Daily Papers

Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a synthetic benchmark and failure atlas built by a clinician. The resource labels medical AI errors by severity from 1 to 5 and safety gate type: missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, and source support gap. The current public release (v0.2.1) contains 44 synthetic cases reviewed by a clinician, with severity annotations, a public Hugging Face Space source, a safety gate taxonomy, a clinical severity rubric, and an automated pipeline for archiving model response screening runs. Forty cases have a populated safety gate field, and four require gate completion. No patient data, clinical validation claims, or model rankings are included. MedFailBench is released under Apache-2.0 and CC-BY-4.0 and carries the Zenodo DOI 10.5281/zenodo.21205535.

Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunately, advances in alignment have significantly reduced the likelihood of harmful model outputs. However, when models are queried billions of times in a day, even rare worst-case behaviors will occur. Current safety evaluations focus on capturing the distribution of inputs that yield harmful outputs. These evaluations disregard the probabilistic nature of models and their tail output behavior. To measure this tail risk, we propose a method to efficiently estimate the probability of harmful outputs for any input query. Instead of naive brute-force sampling from the target model, where harmful outputs could be rare, we operationalize importance sampling by creating unsafe versions of the target model. These unsafe versions enable sample-efficient estimation by making harmful outputs more probable. On benchmarks measuring misuse and misalignment, these estimates match brute-force Monte Carlo estimates using 10-20x fewer samples. For example, we can estimate probability of harmful outputs on the order of 10^-4 with just 500 samples. Additionally, we find that these harmfulness estimates can reveal the sensitivity of models to perturbations in model input and predict deployment risks. Our work demonstrates that accurate rare-event estimation is both critical and feasible for safety evaluations. Code is available at https://github.com/rangell/LMTailRisk

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this purpose, e.g. using models to review the outputs of other models, or red-teaming techniques to surface subtle failure modes. However, researchers have not evaluated whether such techniques still ensure safety if the model is itself intentionally trying to subvert them. In this paper, we develop and evaluate pipelines of safety techniques ("protocols") that are robust to intentional subversion. We investigate a scenario in which we want to solve a sequence of programming problems, using access to a powerful but untrusted model (in our case, GPT-4), access to a less powerful trusted model (in our case, GPT-3.5), and limited access to high-quality trusted labor. We investigate protocols that aim to never submit solutions containing backdoors, which we operationalize here as logical errors that are not caught by test cases. We investigate a range of protocols and test each against strategies that the untrusted model could use to subvert them. One protocol is what we call trusted editing. This protocol first asks GPT-4 to write code, and then asks GPT-3.5 to rate the suspiciousness of that code. If the code is below some suspiciousness threshold, it is submitted. Otherwise, GPT-3.5 edits the solution to remove parts that seem suspicious and then submits the edited code. Another protocol is untrusted monitoring. This protocol asks GPT-4 to write code, and then asks another instance of GPT-4 whether the code is backdoored, using various techniques to prevent the GPT-4 instances from colluding. These protocols improve substantially on simple baselines.

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks. Its decentralized architecture, which separates clients and servers, poses unique challenges for systematic safety analysis. This paper proposes a novel framework to enhance MCP safety. Guided by the MAESTRO framework, we first analyze the missing safety mechanisms in MCP, and based on this analysis, we propose the Model Contextual Integrity Protocol (MCIP), a refined version of MCP that addresses these gaps. Next, we develop a fine-grained taxonomy that captures a diverse range of unsafe behaviors observed in MCP scenarios. Building on this taxonomy, we develop benchmark and training data that support the evaluation and improvement of LLMs' capabilities in identifying safety risks within MCP interactions. Leveraging the proposed benchmark and training data, we conduct extensive experiments on state-of-the-art LLMs. The results highlight LLMs' vulnerabilities in MCP interactions and demonstrate that our approach substantially improves their safety performance.

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit threats such as misuse and prompt injection, but overlook a subtle yet critical setting where user instructions are entirely benign and harm arises from the task context or execution outcome. We introduce OS-BLIND, a benchmark that evaluates CUAs under unintended attack conditions, comprising 300 human-crafted tasks across 12 categories, 8 applications, and 2 threat clusters: environment-embedded threats and agent-initiated harms. Our evaluation on frontier models and agentic frameworks reveals that most CUAs exceed 90% attack success rate (ASR), and even the safety-aligned Claude 4.5 Sonnet reaches 73.0% ASR. More interestingly, this vulnerability becomes even more severe, with ASR rising from 73.0% to 92.7% when Claude 4.5 Sonnet is deployed in multi-agent systems. Our analysis further shows that existing safety defenses provide limited protection when user instructions are benign. Safety alignment primarily activates within the first few steps and rarely re-engages during subsequent execution. In multi-agent systems, decomposed subtasks obscure the harmful intent from the model, causing safety-aligned models to fail. We will release our OS-BLIND to encourage the broader research community to further investigate and address these safety challenges.

Production LLM-agent frameworks expose control primitives -- human-in-the-loop approval gates, run cancellation, and execution timeouts -- whose names and documentation imply barrier semantics: while a run is paused, cancelled, or timed out, no gated side effect executes. We show this implied contract holds on none of the six widely used open-source frameworks we test. Model-free differential probes isolate a recurring sibling leak -- an approval gate suspends its own branch while a sibling branch's effect executes during the pause, so a later rejection cannot prevent it -- in every framework shipping a pre-execution gate (five of six), plus three further gaps: replay double-execution, cancellation orphans, and timeout zombies. The hazard is reachable, not merely constructible: under an a-priori-fixed protocol, frontier models emit the leak-triggering plan shape at pooled rates up to 14%, and when live models drive the unmodified frameworks under an approval pause, 215 of 1,200 runs execute their effect during the pause, across three schedulers and two language runtimes. To repair the measured gaps we present SOUNDGATE, an environment-external effect gate in Rust through which every side effect must be admitted, enforcing hold-until-decided, reject-cancels, dedup-on-replay, and fence-on-cancel -- one property per violation class -- under a stated complete-mediation contract discharged for network egress by kernel-enforced routes. We verify the properties over a model of the admission core (Verus; TLA+/TLC, exhaustive to 7.5e7 states; TLAPS), model-check the deployed Rust with Loom, and bridge model to code by differential conformance over 1.2e7 operations -- refinement evidence, not a mechanized proof. SOUNDGATE blocks every measured violation end-to-end on all six frameworks while releasing legitimate effects, at about 1 ms admission per write and 12k-26k durable admissions per second.

Current evaluations of LLM safety predominantly rely on severity-based taxonomies to assess the harmfulness of malicious queries. We argue that this formulation requires re-examination as it assumes uniform risk across all malicious queries, neglecting Execution Likelihood--the conditional probability of a threat being realized given the model's response. In this work, we introduce Expected Harm, a metric that weights the severity of a jailbreak by its execution likelihood, modeled as a function of execution cost. Through empirical analysis of state-of-the-art models, we reveal a systematic Inverse Risk Calibration: models disproportionately exhibit stronger refusal behaviors for low-likelihood (high-cost) threats while remaining vulnerable to high-likelihood (low-cost) queries. We demonstrate that this miscalibration creates a structural vulnerability: by exploiting this property, we increase the attack success rate of existing jailbreaks by up to 2times. Finally, we trace the root cause of this failure using linear probing, which reveals that while models encode severity in their latent space to drive refusal decisions, they possess no distinguishable internal representation of execution cost, making them "blind" to this critical dimension of risk.

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves high attack success rates across most tested models by systematically exploiting the model's ethical reasoning capabilities to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility.

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due to untrusted external tools. While prior work has focused on attacks injected through external tool outputs, we investigate a more fundamental vulnerability: Tool Poisoning, where malicious instructions are embedded within a tool's metadata without execution. To date, this threat has been primarily demonstrated through isolated cases, lacking a systematic, large-scale evaluation. We introduce MCPTox, the first benchmark to systematically evaluate agent robustness against Tool Poisoning in realistic MCP settings. MCPTox is constructed upon 45 live, real-world MCP servers and 353 authentic tools. To achieve this, we design three distinct attack templates to generate a comprehensive suite of 1312 malicious test cases by few-shot learning, covering 10 categories of potential risks. Our evaluation on 20 prominent LLM agents setting reveals a widespread vulnerability to Tool Poisoning, with o1-mini, achieving an attack success rate of 72.8\%. We find that more capable models are often more susceptible, as the attack exploits their superior instruction-following abilities. Finally, the failure case analysis reveals that agents rarely refuse these attacks, with the highest refused rate (Claude-3.7-Sonnet) less than 3\%, demonstrating that existing safety alignment is ineffective against malicious actions that use legitimate tools for unauthorized operation. Our findings create a crucial empirical baseline for understanding and mitigating this widespread threat, and we release MCPTox for the development of verifiably safer AI agents. Our dataset is available at an anonymized repository: https://anonymous.4open.science/r/AAAI26-7C02.

Training large language models to follow instructions makes them perform better on a wide range of tasks, generally becoming more helpful. However, a perfectly helpful model will follow even the most malicious instructions and readily generate harmful content. In this paper, we raise concerns over the safety of models that only emphasize helpfulness, not safety, in their instruction-tuning. We show that several popular instruction-tuned models are highly unsafe. Moreover, we show that adding just 3% safety examples (a few hundred demonstrations) in the training set when fine-tuning a model like LLaMA can substantially improve their safety. Our safety-tuning does not make models significantly less capable or helpful as measured by standard benchmarks. However, we do find a behavior of exaggerated safety, where too much safety-tuning makes models refuse to respond to reasonable prompts that superficially resemble unsafe ones. Our study sheds light on trade-offs in training LLMs to follow instructions and exhibit safe behavior.

Text-to-image models trained on large-scale data often inevitably ingest unsafe content. While some people observe input-output amplifications, it remains unclear whether and how training data composition directly drives model output safety or by other factors. We shed light on this question by isolating this variable: we train the same text-to-image model on datasets that differ only in their fraction of unsafe images (0\% to 9.6\%), across several dataset scales (100K to 8M). Then we generate images with the resulting models, and evaluate them with four independent safety classifiers. Output unsafety rises monotonically from 16.6\% at 0\% contamination to 25.5\% at 5\%. A factorial design reveals that the proportion, not the absolute count, of unsafe training images is the operative variable. The 16.6\% irreducible baseline at zero contamination implicates the other components, e.g. frozen text encoder, as a residual safety risk -- confirmed by a text encoder ablation showing that SafeCLIP reduces this floor to 9.6\%, while the dose-response effect persists across all three encoders tested. Critically, no quality degradation in terms of FID, CLIPscore and ImageReward accompanies safety filtering. These results establish that data curation and text encoder safety are complementary and independently effective interventions. At the same time, the remaining level of unsafety poses questions for future research about emerging capabilities and compositionality.

This position paper argues that computer science conferences should require tamper-evident, nonrepudiable attestations of experimental results. We name the underlying problem experiment nonrepudiation: a compliant protocol must bind the numbers in a paper to an actual executed computation in a way the author cannot later alter or deny. The current system relies on self-reported checklists, optional code sharing, and author-controlled logging. None of these mechanisms answer the question a reviewer cannot check: did the code the paper describes produce the numbers the paper reports? We define the problem formally, state the security properties any compliant protocol must satisfy, and describe a threat model that includes attacks current approaches do not prevent. To show that the problem is solvable, we built K-Veritas, a reference implementation in Go that produces signed reports without accessing training data. K-Veritas is a testbed, not a finished answer. We call on conferences and the community to treat nonrepudiation as a first-class requirement and to help build an open, independent standard for it.

Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatGPT that elicit undesired behavior. Going beyond recognition of the issue, we investigate why such attacks succeed and how they can be created. We hypothesize two failure modes of safety training: competing objectives and mismatched generalization. Competing objectives arise when a model's capabilities and safety goals conflict, while mismatched generalization occurs when safety training fails to generalize to a domain for which capabilities exist. We use these failure modes to guide jailbreak design and then evaluate state-of-the-art models, including OpenAI's GPT-4 and Anthropic's Claude v1.3, against both existing and newly designed attacks. We find that vulnerabilities persist despite the extensive red-teaming and safety-training efforts behind these models. Notably, new attacks utilizing our failure modes succeed on every prompt in a collection of unsafe requests from the models' red-teaming evaluation sets and outperform existing ad hoc jailbreaks. Our analysis emphasizes the need for safety-capability parity -- that safety mechanisms should be as sophisticated as the underlying model -- and argues against the idea that scaling alone can resolve these safety failure modes.

Consider a scenario where a harmfulness evaluation metric intended to filter unsafe responses from a Large Language Model. When applied to individual harmful prompt-response pairs, it correctly flags them as unsafe by assigning a high-risk score. Yet, if those same pairs are concatenated, the metrics decision unexpectedly reverses - labelling the combined content as safe with a low score, allowing the harmful text to bypass the filter. We found that multiple safety metrics, including advanced metrics such as GPT-based judges, exhibit this non-safe behaviour. Moreover, they show a strong sensitivity to input order: responses are often classified as safe if safe content appears first, regardless of any harmful content that follows, and vice versa. These findings underscore the importance of evaluating the safety of safety metrics, that is, the reliability of their output scores. To address this, we developed general, automatic, concatenation-based tests to assess key properties of these metrics. When applied in a model safety scenario, the tests revealed significant inconsistencies in harmfulness evaluations.

Safety-aligned language models often exhibit fragile and imbalanced safety mechanisms, increasing the likelihood of generating unsafe content. In addition, incorporating new knowledge through editing techniques to language models can further compromise safety. To address these issues, we propose SafeInfer, a context-adaptive, decoding-time safety alignment strategy for generating safe responses to user queries. SafeInfer comprises two phases: the safety amplification phase, which employs safe demonstration examples to adjust the model's hidden states and increase the likelihood of safer outputs, and the safety-guided decoding phase, which influences token selection based on safety-optimized distributions, ensuring the generated content complies with ethical guidelines. Further, we present HarmEval, a novel benchmark for extensive safety evaluations, designed to address potential misuse scenarios in accordance with the policies of leading AI tech giants.

LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed safety violations, and the corresponding outcomes are evaluated by hard-coded rules, making them costly to extend as agents evolve. To this end, we present Vera, an end-to-end automated safety testing framework that instantiates software engineering testing principles for non-deterministic agents through a three-stage, self-reinforcing pipeline. First, a literature-driven exploration continuously discovers and structures emerging risks into taxonomies of safety risks, attack methods, and tool execution environments. Second, combinatorial composition across taxonomy dimensions produces executable safety cases, each specifying a concrete safety goal, a programmatically constructed initial state, and a deterministic verification predicate grounded in observable artifacts. Third, adaptive execution runs heterogeneous agents in isolated sandboxes where a control agent steers multi-turn interaction based on runtime observations, while evidence-grounded verifiers judge outcomes from environment state and tool-call evidence rather than model self-report. We evaluate Vera on four production agent frameworks (OpenClaw, Hermes, Codex, Claude Code), revealing substantial safety weaknesses, with average attack success rates reaching 93.9\% under multi-channel attacks; we also release Vera-Bench, comprising 1600 executable safety cases spanning 124 risk categories across three execution settings. These results indicate that modular, executable testing infrastructure is essential for rigorous and maintainable safety evaluation of rapidly evolving agentic systems at scale. The code is publicly available at https://github.com/Yunhao-Feng/Vera.

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during pretraining, they are hard to remove. We present a data-centric pretraining framework that builds safety into the model from the start. Our contributions include: (i) a safety classifier trained on 10,000 GPT-4 labeled examples, used to filter 600B tokens; (ii) the largest synthetic safety dataset to date (100B tokens) generated via recontextualization of harmful web data; (iii) RefuseWeb and Moral Education datasets that convert harmful prompts into refusal dialogues and web-style educational material; (iv) Harmfulness-Tag annotations injected during pretraining to flag unsafe content and steer away inference from harmful generations; and (v) safety evaluations measuring base model behavior before instruction tuning. Our safety-pretrained models reduce attack success rates from 38.8% to 8.4% with no performance degradation on standard LLM safety benchmarks.

Despite the remarkable synthesis capabilities of text-to-image (T2I) models, safeguarding them against content violations remains a persistent challenge. Existing safety alignments primarily focus on explicit malicious concepts, often overlooking the subtle yet critical risks of compositional semantics. To address this oversight, we identify and formalize a novel vulnerability: Multi-Concept Compositional Unsafety (MCCU), where unsafe semantics stem from the implicit associations of individually benign concepts. Based on this formulation, we introduce TwoHamsters, a comprehensive benchmark comprising 17.5k prompts curated to probe MCCU vulnerabilities. Through a rigorous evaluation of 10 state-of-the-art models and 16 defense mechanisms, our analysis yields 8 pivotal insights. In particular, we demonstrate that current T2I models and defense mechanisms face severe MCCU risks: on TwoHamsters, FLUX achieves an MCCU generation success rate of 99.52%, while LLaVA-Guard only attains a recall of 41.06%, highlighting a critical limitation of the current paradigm for managing hazardous compositional generation.

SCTP is a transport protocol offering features such as multi-homing, multi-streaming, and message-oriented delivery. Its two main implementations were subjected to conformance tests using the PacketDrill tool. Conformance testing is not exhaustive and a recent vulnerability (CVE-2021-3772) showed SCTP is not immune to attacks. Changes addressing the vulnerability were implemented, but the question remains whether other flaws might persist in the protocol design. We study the security of the SCTP design, taking a rigorous approach rooted in formal methods. We create a formal Promela model of SCTP, and define 10 properties capturing the essential protocol functionality based on its RFC specification and consultation with the lead RFC author. Then we show using the Spin model checker that our model satisfies these properties. We define 4 attacker models - Off-Path, where the attacker is an outsider that can spoof the port and IP of a peer; Evil-Server, where the attacker is a malicious peer; Replay, where an attacker can capture and replay, but not modify, packets; and On-Path, where the attacker controls the channel between peers. We modify an attack synthesis tool designed for transport protocols, Korg, to support our SCTP model and four attacker models. We synthesize 14 unique attacks using the attacker models - including the CVE vulnerability in the Off-Path attacker model, 4 attacks in the Evil-Server attacker model, an opportunistic ABORT attack in the Replay attacker model, and eight connection manipulation attacks in the On-Path attacker model. We show that the proposed patch eliminates the vulnerability and does not introduce new ones according to our model and protocol properties. Finally, we identify and analyze an ambiguity in the RFC, which we show can be interpreted insecurely. We propose an erratum and show that it eliminates the ambiguity.

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from acting on user-provided content. Existing studies on agent security largely focus on model-internal vulnerabilities or adversarial access to agent interfaces, overlooking attacks that exploit users as unintended conduits. In this paper, we study user-mediated attacks, where benign users are tricked into relaying untrusted or attacker-controlled content to agents, and analyze how commercial LLM agents respond under such conditions. We conduct a systematic evaluation of 12 commercial agents in a sandboxed environment, covering 6 trip-planning agents and 6 web-use agents, and compare agent behavior across scenarios with no, soft, and hard user-requested safety checks. Our results show that agents are too helpful to be safe by default. Without explicit safety requests, trip-planning agents bypass safety constraints in over 92% of cases, converting unverified content into confident booking guidance. Web-use agents exhibit near-deterministic execution of risky actions, with 9 out of 17 supported tests reaching a 100% bypass rate. Even when users express soft or hard safety intent, constraint bypass remains substantial, reaching up to 54.7% and 7% for trip-planning agents, respectively. These findings reveal that the primary issue is not a lack of safety capability, but its prioritization. Agents invoke safety checks only conditionally when explicitly prompted, and otherwise default to goal-driven execution. Moreover, agents lack clear task boundaries and stopping rules, frequently over-executing workflows in ways that lead to unnecessary data disclosure and real-world harm.

As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial framework for testing deployment strategies of untrusted models (i.e., models which might be trying to bypass safety measures). While prior work treats a single failure as unacceptable, we perform control evaluations in a "distributed threat setting" -- a setting where no single action is catastrophic and no single action provides overwhelming evidence of misalignment. We approach this problem with a two-level deployment framework that uses an adaptive macro-protocol to choose between micro-protocols. Micro-protocols operate on a single task, using a less capable, but extensively tested (trusted) model to harness and monitor the untrusted model. Meanwhile, the macro-protocol maintains an adaptive credence on the untrusted model's alignment based on its past actions, using it to pick between safer and riskier micro-protocols. We evaluate our method in a code generation testbed where a red team attempts to generate subtly backdoored code with an LLM whose deployment is safeguarded by a blue team. We plot Pareto frontiers of safety (# of non-backdoored solutions) and usefulness (# of correct solutions). At a given level of usefulness, our adaptive deployment strategy reduces the number of backdoors by 80% compared to non-adaptive baselines.

As Artificial General Intelligence (AGI) becomes increasingly integrated into various facets of human life, ensuring the safety and ethical alignment of such systems is paramount. Previous studies primarily focus on single-modality threats, which may not suffice given the integrated and complex nature of cross-modality interactions. We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment. Specifically, it considers cases where single modalities are safe independently but could potentially lead to unsafe or unethical outputs when combined. To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations. Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, such as GPT-4V and LLaVA, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.

Computer use agents are LLM-based agents that can directly interact with a graphical user interface, by processing screenshots or accessibility trees. While these systems are gaining popularity, their safety has been largely overlooked, despite the fact that evaluating and understanding their potential for harmful behavior is essential for widespread adoption. To address this gap, we introduce OS-Harm, a new benchmark for measuring safety of computer use agents. OS-Harm is built on top of the OSWorld environment and aims to test models across three categories of harm: deliberate user misuse, prompt injection attacks, and model misbehavior. To cover these cases, we create 150 tasks that span several types of safety violations (harassment, copyright infringement, disinformation, data exfiltration, etc.) and require the agent to interact with a variety of OS applications (email client, code editor, browser, etc.). Moreover, we propose an automated judge to evaluate both accuracy and safety of agents that achieves high agreement with human annotations (0.76 and 0.79 F1 score). We evaluate computer use agents based on a range of frontier models - such as o4-mini, Claude 3.7 Sonnet, Gemini 2.5 Pro - and provide insights into their safety. In particular, all models tend to directly comply with many deliberate misuse queries, are relatively vulnerable to static prompt injections, and occasionally perform unsafe actions. The OS-Harm benchmark is available at https://github.com/tml-epfl/os-harm.

Large language models (LLMs) are evolving into agentic systems that reason, plan, and operate external tools. The Model Context Protocol (MCP) is a key enabler of this transition, offering a standardized interface for connecting LLMs with heterogeneous tools and services. Yet MCP's openness and multi-server workflows introduce new safety risks that existing benchmarks fail to capture, as they focus on isolated attacks or lack real-world coverage. We present MCP-SafetyBench, a comprehensive benchmark built on real MCP servers that supports realistic multi-turn evaluation across five domains: browser automation, financial analysis, location navigation, repository management, and web search. It incorporates a unified taxonomy of 20 MCP attack types spanning server, host, and user sides, and includes tasks requiring multi-step reasoning and cross-server coordination under uncertainty. Using MCP-SafetyBench, we systematically evaluate leading open- and closed-source LLMs, revealing that all models remain vulnerable to MCP attacks, with a notable safety-utility trade-off. Our results highlight the urgent need for stronger defenses and establish MCP-SafetyBench as a foundation for diagnosing and mitigating safety risks in real-world MCP deployments.

Large language models are increasingly deployed as coding agents, shifting safety from individual responses to action sequences. Existing benchmarks, however, primarily assess whether models refuse unsafe prompts, leaving impacts on stateful workspaces largely unexamined. We present SABER, a benchmark for environment-aware operational safety that places models in realistic agent-style projects and evaluates safety from the final environment state after a sequence of actions. Beyond binary safety-violation reports, SABER categorizes violations by cause, enabling analysis of model-specific safety profiles. Our evaluations show that even the best-performing model has more than a 54% harmful safety-violation rate (HSR), suggesting that current alignment remains insufficient for realistic project environments. SABER further reveals distinct safety profiles across models. Our benchmark is publicly available at https://github.com/sssr-lab/saber.

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. This creates a distinct safety challenge in that harmful behavior may emerge through sequences of individually plausible steps, including intermediate actions that appear locally acceptable but collectively lead to unauthorized actions. We present AgentHazard, a benchmark for evaluating harmful behavior in computer-use agents. AgentHazard contains 2,653 instances spanning diverse risk categories and attack strategies. Each instance pairs a harmful objective with a sequence of operational steps that are locally legitimate but jointly induce unsafe behavior. The benchmark evaluates whether agents can recognize and interrupt harm arising from accumulated context, repeated tool use, intermediate actions, and dependencies across steps. We evaluate AgentHazard on Claude Code, OpenClaw, and IFlow using mostly open or openly deployable models from the Qwen3, Kimi, GLM, and DeepSeek families. Our experimental results indicate that current systems remain highly vulnerable. In particular, when powered by Qwen3-Coder, Claude Code exhibits an attack success rate of 73.63\%, suggesting that model alignment alone does not reliably guarantee the safety of autonomous agents.

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful outputs but can degrade reasoning depth, leading to significant trade-offs in complex, multi-step tasks, and remain vulnerable to sophisticated jailbreak attacks. To address this, we introduce SAFEPATH, a lightweight alignment method that fine-tunes LRMs to emit a short, 8-token Safety Primer at the start of their reasoning, in response to harmful prompts, while leaving the rest of the reasoning process unsupervised. Empirical results across multiple benchmarks indicate that SAFEPATH effectively reduces harmful outputs while maintaining reasoning performance. Specifically, SAFEPATH reduces harmful responses by up to 90.0% and blocks 83.3% of jailbreak attempts in the DeepSeek-R1-Distill-Llama-8B model, while requiring 295.9x less compute than Direct Refusal and 314.1x less than SafeChain. We further introduce a zero-shot variant that requires no fine-tuning. In addition, we provide a comprehensive analysis of how existing methods in LLMs generalize, or fail, when applied to reasoning-centric models, revealing critical gaps and new directions for safer AI.

With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant barriers to the real-world deployment of these agents. To provide comprehensive and practical evaluations on the safety of code agents, we propose RedCode, a benchmark for risky code execution and generation: (1) RedCode-Exec provides challenging prompts that could lead to risky code execution, aiming to evaluate code agents' ability to recognize and handle unsafe code. We provide a total of 4,050 risky test cases in Python and Bash tasks with diverse input formats including code snippets and natural text. They covers 25 types of critical vulnerabilities spanning 8 domains (e.g., websites, file systems). We provide Docker environments and design corresponding evaluation metrics to assess their execution results. (2) RedCode-Gen provides 160 prompts with function signatures and docstrings as input to assess whether code agents will follow instructions to generate harmful code or software. Our empirical findings, derived from evaluating three agent frameworks based on 19 LLMs, provide insights into code agents' vulnerabilities. For instance, evaluations on RedCode-Exec show that agents are more likely to reject executing risky operations on the operating system, but are less likely to reject executing technically buggy code, indicating high risks. Risky operations described in natural text lead to a lower rejection rate than those in code format. Additionally, evaluations on RedCode-Gen show that more capable base models and agents with stronger overall coding abilities, such as GPT4, tend to produce more sophisticated and effective harmful software. Our findings highlight the need for stringent safety evaluations for diverse code agents. Our dataset and code are available at https://github.com/AI-secure/RedCode.

Fine-tuning large language models (LLMs) for telecom tasks and datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent research has shown that even benign fine-tuning can degrade the safety alignment of LLMs, causing them to respond to harmful or unethical user queries. In this paper, we investigate this issue for telecom-tuned LLMs using three representative datasets featured by the GenAINet initiative. We show that safety degradation persists even for structured and seemingly harmless datasets such as 3GPP standards and tabular records, indicating that telecom-specific data is not immune to safety erosion during fine-tuning. We further extend our analysis to publicly available Telecom LLMs trained via continual pre-training, revealing that safety alignment is often severely lacking, primarily due to the omission of safety-focused instruction tuning. To address these issues in both fine-tuned and pre-trained models, we conduct extensive experiments and evaluate three safety realignment defenses (SafeInstruct, SafeLoRA, and SafeMERGE) using established red-teaming benchmarks. The results show that, across all settings, the proposed defenses can effectively restore safety after harmful degradation without compromising downstream task performance, leading to Safe teleCOMMunication (SafeCOMM) models. In a nutshell, our work serves as a diagnostic study and practical guide for safety realignment in telecom-tuned LLMs, and emphasizes the importance of safety-aware instruction and fine-tuning for real-world deployments of Telecom LLMs.

The development of machine learning (ML) techniques has led to ample opportunities for developers to develop and deploy their own models. Hugging Face serves as an open source platform where developers can share and download other models in an effort to make ML development more collaborative. In order for models to be shared, they first need to be serialized. Certain Python serialization methods are considered unsafe, as they are vulnerable to object injection. This paper investigates the pervasiveness of these unsafe serialization methods across Hugging Face, and demonstrates through an exploitation approach, that models using unsafe serialization methods can be exploited and shared, creating an unsafe environment for ML developers. We investigate to what extent Hugging Face is able to flag repositories and files using unsafe serialization methods, and develop a technique to detect malicious models. Our results show that Hugging Face is home to a wide range of potentially vulnerable models.

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows; however, prompt injection attacks can steer these systems toward clinically unsafe or misleading outputs. We introduce the Medical Prompt Injection Benchmark (MPIB), a dataset-and-benchmark suite for evaluating clinical safety under both direct prompt injection and indirect, RAG-mediated injection across clinically grounded tasks. MPIB emphasizes outcome-level risk via the Clinical Harm Event Rate (CHER), which measures high-severity clinical harm events under a clinically grounded taxonomy, and reports CHER alongside Attack Success Rate (ASR) to disentangle instruction compliance from downstream patient risk. The benchmark comprises 9,697 curated instances constructed through multi-stage quality gates and clinical safety linting. Evaluating MPIB across a diverse set of baseline LLMs and defense configurations, we find that ASR and CHER can diverge substantially, and that robustness depends critically on whether adversarial instructions appear in the user query or in retrieved context. We release MPIB with evaluation code, adversarial baselines, and comprehensive documentation to support reproducible and systematic research on clinical prompt injection. Code and data are available at GitHub (code) and Hugging Face (data).

Network protocols are programs with inputs and outputs that follow predefined communication patterns to synchronize and exchange information. There are many protocols and each serves a different purpose, e.g., routing, transport, secure communication, etc. The functional and performance requirements for a protocol can be expressed using a formal specification, such as, a set of logical predicates over its traces. A protocol could be prevented from achieving its requirements due to a bug in its design or implementation, a component failure (e.g., a crash), or an attack. This dissertation shows that formal methods can feasibly characterize the functionality and performance of network protocols under normal conditions as well as when subjected to attacks.

As large reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses, while overlooking hard prompts that always elicit harmful outputs. To fill this gap, we introduce UnsafeChain, a safety alignment dataset constructed from hard prompts with diverse sources, where unsafe completions are identified and explicitly corrected into safe responses. By exposing models to unsafe behaviors and guiding their correction, UnsafeChain enhances safety while preserving general reasoning ability. We fine-tune three LRMs on UnsafeChain and compare them against recent SafeChain and STAR-1 across six out-of-distribution and five in-distribution benchmarks. UnsafeChain consistently outperforms prior datasets, with even a 1K subset matching or surpassing baseline performance, demonstrating the effectiveness and generalizability of correction-based supervision. We release our dataset and code at https://github.com/mbzuai-nlp/UnsafeChain

The popularity of the Rust language continues to explode; yet, many critical codebases remain authored in C, and cannot be realistically rewritten by hand. Automatically translating C to Rust is thus an appealing course of action. Several works have gone down this path, handling an ever-increasing subset of C through a variety of Rust features, such as unsafe. While the prospect of automation is appealing, producing code that relies on unsafe negates the memory safety guarantees offered by Rust, and therefore the main advantages of porting existing codebases to memory-safe languages. We instead explore a different path, and explore what it would take to translate C to safe Rust; that is, to produce code that is trivially memory safe, because it abides by Rust's type system without caveats. Our work sports several original contributions: a type-directed translation from (a subset of) C to safe Rust; a novel static analysis based on "split trees" that allows expressing C's pointer arithmetic using Rust's slices and splitting operations; an analysis that infers exactly which borrows need to be mutable; and a compilation strategy for C's struct types that is compatible with Rust's distinction between non-owned and owned allocations. We apply our methodology to existing formally verified C codebases: the HACL* cryptographic library, and binary parsers and serializers from EverParse, and show that the subset of C we support is sufficient to translate both applications to safe Rust. Our evaluation shows that for the few places that do violate Rust's aliasing discipline, automated, surgical rewrites suffice; and that the few strategic copies we insert have a negligible performance impact. Of particular note, the application of our approach to HACL* results in a 80,000 line verified cryptographic library, written in pure Rust, that implements all modern algorithms - the first of its kind.

Memory-safety bugs introduce critical software-security issues. Rust provides memory-safe mechanisms to avoid memory-safety bugs in programming, while still allowing unsafe escape hatches via unsafe code. However, the unsafe code that enhances the usability of Rust provides clear spots for finding memory-safety bugs in Rust source code. In this paper, we claim that these unsafe spots can still be identifiable in Rust binary code via machine learning and be leveraged for finding memory-safety bugs. To support our claim, we propose the tool textttrustspot, that enables reverse engineering to learn an unsafe classifier that proposes a list of functions in Rust binaries for downstream analysis. We empirically show that the function proposals by textttrustspot can recall 92.92% of memory-safety bugs, while it covers only 16.79% of the entire binary code. As an application, we demonstrate that the function proposals are used in targeted fuzzing on Rust packages, which contribute to reducing the fuzzing time compared to non-targeted fuzzing.

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing benchmarks either evaluate safety at the semantic layer alone, missing physical-layer harms, or fail to isolate test cases, letting earlier runs contaminate later ones. We present LITMUS (LLM-agents In-OS Testing for Measuring Unsafe Subversion), a benchmark addressing both gaps via a semantic-physical dual verification mechanism and OS-level state rollback. LITMUS comprises 819 high-risk test cases organized into one harmful seed subset and six attack-extended subsets covering three adversarial paradigms (jailbreak speaking, skill injection, and entity wrapping), plus a fully automated multi-agent evaluation framework judging behavior at both conversational and OS-level physical layers. Evaluation across frontier agents reveals three findings: (1) current agents lack effective safety awareness, with strong models (e.g., Claude Sonnet 4.6) still executing 40.64% of high-risk operations; (2) agents exhibit pervasive Execution Hallucination (EH), verbally refusing a request while the dangerous operation has already completed at the system level, invisible to every prior semantic-only framework; and (3) skill injection and entity wrapping attacks achieve high success rates, exposing pronounced agent vulnerabilities. LITMUS provides the first standardized platform for reproducible, physically grounded behavioral safety evaluation of LLM agents in real OS environments.

Although Large Reasoning Models (LRMs) have progressed in solving complex problems, their chain-of-thought (CoT) reasoning often contains harmful content that can persist even when the final responses appear safe. We show that this issue still remains in existing methods which overlook the unique significance of safe reasoning, undermining their trustworthiness and posing potential risks in applications if unsafe reasoning is accessible for and exploited by malicious users. We therefore shift our focus to aligning the safety of reasoning itself in this paper and explore process supervision as the solution. However, simply rewarding safe reasoning proves inadequate due to low rollout diversity and limited training signals. To tackle this challenge, we first delve into the characteristics of safe reasoning and uncover several critical insights that 1) safe reasoning is often consolidated by a few critical steps of safety triggers; 2) compliance cues strongly correlate with unsafe continuations; and 3) corrective interventions reliably steer unsafe trajectories towards safer traces. Motivated by these, we propose Intervened Preference Optimization (IPO), an alignment method that enforces safe reasoning by substituting compliance steps with safety triggers and constructing pairs for preference learning with strong signals. Experiments on jailbreak and adversarial safety benchmarks demonstrate that IPO remarkably improves overall safety regarding both reasoning and responses, outperforming SFT-based and RL-based baselines with a relative reduction of over 30% in harmfulness, while preserving excellent performance across diverse reasoning tasks. The results highlight the importance of explicit alignment for reasoning and provide a practical path to safer LRMs.

AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions. Yet LLMs often become substantially less safe when deployed as agents, and the source of this degradation remains poorly understood. In this paper, we identify schema-formatted tool specifications as a primary source of agent safety degradation and show, through white-box representation analysis, that they weaken the model's internal refusal signals and contribute to unsafe tool execution. Building on this finding, we propose SafeKeep, an inference-time safeguard that decouples safety judgment from tool execution: it assesses requests using flattened textual tool specifications while retaining the original schema-formatted specifications for execution. Across two representative benchmarks and four LLMs, including both white-box and black-box models, SafeKeep increases the average refusal rate for harmful requests from 23.8% to 70.6% and reduces the average attack success rate under observation-level prompt injection from 25.6% to 2.5%. It also outperforms existing safeguards and preserves task-handling capability. We release the code and data at https://github.com/snowcatsmoking/SafeKeep .

As large language models (LLMs) become high-privilege agents in risk-sensitive settings, they introduce systemic threats beyond hallucination, where minor compliance errors can cause critical data leaks. However, existing benchmarks focus on rule-based QA, lacking agentic execution modeling, overlooking compliance drift in adversarial interactions, and relying on binary safety metrics that fail to capture behavioral degradation. To bridge these gaps, we present CNFinBench, a comprehensive benchmark spanning 29 subtasks grounded in the triad of expertise, autonomy, and integrity. It assesses domain-specific capabilities through certified regulatory corpora and professional financial tasks, reconstructs end-to-end agent workflows from requirement parsing to tool verification, and simulates multi-turn adversarial attacks that induce behavioral compliance drift. To quantify safety degradation, we introduce the Harmful Instruction Compliance Score (HICS), a multi-dimensional safety metric that integrates risk-type-specific deductions, multi-turn consistency tracking, and severity-adjusted penalty scaling based on fine-grained violation triggers. Evaluations over 22 open-/closed-source models reveal: LLMs perform well in applied tasks yet lack robust rule understanding, suffer a 15.4-point drop single modules to full execution chains, and collapse rapidly in multi-turn attacks, with average violations surging by 172.3% in Round 2. CNFinBench is available at https://cnfinbench.opencompass.org.cn and https://github.com/VertiAIBench/CNFinBench.

LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that only emerge during actual execution. In this work, we conduct a systematic investigation into how well current agent systems recognize and avoid such risks. To support quantitative and qualitative evaluation, we construct OpenSkillRisk, a dedicated safety benchmark containing 263 risky skills collected from public skill marketplaces. We classify these skills into seven categories based on their threat types and pair each skill with a standardized user task and a corresponding sandbox for controlled evaluation. Distinct from prior benchmarks, OpenSkillRisk not only covers more realistic and diverse unsafe scenarios, but also provides a fine-grained analysis to diagnose the behavioral patterns of agents in such scenarios. We conduct comprehensive experiments covering three mainstream CLI agent frameworks and thirteen state-of-the-art LLMs. Experimental results show that no tested system handles risky skills reliably: even the safest configurations still execute unsafe actions in about 17% of cases. Context-dependent and system-level risks are especially difficult for current agent systems to avoid. Our behavioral analysis reveals three recurring failure patterns: agents may fail to recognize the risk, recognize it but fail to intervene before acting, or follow skill instructions beyond the user's intended scope. These findings highlight the need to improve both risk reasoning in LLMs and execution control in agent frameworks.

Leading language model (LM) providers like OpenAI and Google offer fine-tuning APIs that allow customers to adapt LMs for specific use cases. To prevent misuse, these LM providers implement filtering mechanisms to block harmful fine-tuning data. Consequently, adversaries seeking to produce unsafe LMs via these APIs must craft adversarial training data that are not identifiably harmful. We make three contributions in this context: 1. We show that many existing attacks that use harmless data to create unsafe LMs rely on eliminating model refusals in the first few tokens of their responses. 2. We show that such prior attacks can be blocked by a simple defense that pre-fills the first few tokens from an aligned model before letting the fine-tuned model fill in the rest. 3. We describe a new data-poisoning attack, ``No, Of course I Can Execute'' (NOICE), which exploits an LM's formulaic refusal mechanism to elicit harmful responses. By training an LM to refuse benign requests on the basis of safety before fulfilling those requests regardless, we are able to jailbreak several open-source models and a closed-source model (GPT-4o). We show an attack success rate (ASR) of 57% against GPT-4o; our attack earned a Bug Bounty from OpenAI. Against open-source models protected by simple defenses, we improve ASRs by an average of 3.25 times compared to the best performing previous attacks that use only harmless data. NOICE demonstrates the exploitability of repetitive refusal mechanisms and broadens understanding of the threats closed-source models face from harmless data.

Large Language Models (LLMs) have become an integral part of our daily lives. However, they impose certain risks, including those that can harm individuals' privacy, perpetuate biases and spread misinformation. These risks highlight the need for robust safety mechanisms, ethical guidelines, and thorough testing to ensure their responsible deployment. Safety of LLMs is a key property that needs to be thoroughly tested prior the model to be deployed and accessible to the general users. This paper reports the external safety testing experience conducted by researchers from Mondragon University and University of Seville on OpenAI's new o3-mini LLM as part of OpenAI's early access for safety testing program. In particular, we apply our tool, ASTRAL, to automatically and systematically generate up to date unsafe test inputs (i.e., prompts) that helps us test and assess different safety categories of LLMs. We automatically generate and execute a total of 10,080 unsafe test input on a early o3-mini beta version. After manually verifying the test cases classified as unsafe by ASTRAL, we identify a total of 87 actual instances of unsafe LLM behavior. We highlight key insights and findings uncovered during the pre-deployment external testing phase of OpenAI's latest LLM.

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection. This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem over evolving interaction trajectories. The proposed design separates execution governance from semantic risk reasoning through two coordinated components: a runtime controller that mediates actions around the agent loop and a context-aware decision core that operates over persistent session state. The core is formalized as a context-aware advanced machine intelligence and instantiated through operators for risk encoding, utility-cost evaluation, consequence modeling, policy arbitration, and state synchronization. Experiments on Agent Security Bench (ASB) and InjecAgent show that SafeAgent consistently improves robustness over baseline and text-level guardrail methods while maintaining competitive benign-task performance. Ablation studies further show that recovery confidence and policy weighting determine distinct safety-utility operating points.

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both helpful and harmless. However, there is a tension between these two objectives, since harmlessness requires models to refuse complying with unsafe prompts, and thus not be helpful. Recent anecdotal evidence suggests that some models may have struck a poor balance, so that even clearly safe prompts are refused if they use similar language to unsafe prompts or mention sensitive topics. In this paper, we introduce a new test suite called XSTest to identify such eXaggerated Safety behaviours in a structured and systematic way. In its current form, XSTest comprises 200 safe prompts across ten prompt types that well-calibrated models should not refuse to comply with. We describe XSTest's creation and composition, and use the test suite to highlight systematic failure modes in a recently-released state-of-the-art language model.

Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel benchmark to quantify LLM security risks and capabilities. We introduce two new areas for testing: prompt injection and code interpreter abuse. We evaluated multiple state-of-the-art (SOTA) LLMs, including GPT-4, Mistral, Meta Llama 3 70B-Instruct, and Code Llama. Our results show that conditioning away risk of attack remains an unsolved problem; for example, all tested models showed between 26% and 41% successful prompt injection tests. We further introduce the safety-utility tradeoff: conditioning an LLM to reject unsafe prompts can cause the LLM to falsely reject answering benign prompts, which lowers utility. We propose quantifying this tradeoff using False Refusal Rate (FRR). As an illustration, we introduce a novel test set to quantify FRR for cyberattack helpfulness risk. We find many LLMs able to successfully comply with "borderline" benign requests while still rejecting most unsafe requests. Finally, we quantify the utility of LLMs for automating a core cybersecurity task, that of exploiting software vulnerabilities. This is important because the offensive capabilities of LLMs are of intense interest; we quantify this by creating novel test sets for four representative problems. We find that models with coding capabilities perform better than those without, but that further work is needed for LLMs to become proficient at exploit generation. Our code is open source and can be used to evaluate other LLMs.

Modern language models (LMs) have gained widespread acceptance in everyday and professional contexts, particularly in programming. An essential procedure enabling this adoption is instruction tuning, which substantially enhances LMs' practical utility by training them to follow user instructions and human preferences. However, existing instruction tuning schemes overlook a crucial aspect: the security of generated code. As a result, even the state-of-the-art instruction-tuned LMs frequently produce unsafe code, posing significant security risks. In this work, we introduce SafeCoder to address this gap. SafeCoder performs security-centric fine-tuning using a diverse and high-quality dataset that we collected using an automated pipeline. We integrate the security fine-tuning with standard instruction tuning, to facilitate a joint optimization of both security and utility. Despite its simplicity, we show that SafeCoder is effective across a variety of popular LMs and datasets. It is able to drastically improve security (by about 30%), while preserving utility.

Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety mechanisms can be bypassed by ablating or removing specific representational directions within the model. In this paper, we propose the opposite approach: Rank-One Safety Injection (ROSI), a white-box method that amplifies a model's safety alignment by permanently steering its activations toward the refusal-mediating subspace. ROSI operates as a simple, fine-tuning-free rank-one weight modification applied to all residual stream write matrices. The required safety direction can be computed from a small set of harmful and harmless instruction pairs. We show that ROSI consistently increases safety refusal rates - as evaluated by Llama Guard 3 - while preserving the utility of the model on standard benchmarks such as MMLU, HellaSwag, and Arc. Furthermore, we show that ROSI can also re-align 'uncensored' models by amplifying their own latent safety directions, demonstrating its utility as an effective last-mile safety procedure. Our results suggest that targeted, interpretable weight steering is a cheap and potent mechanism to improve LLM safety, complementing more resource-intensive fine-tuning paradigms.

Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing benchmarks rely on simplified environments and fail to capture realistic, stateful, multi-service workflows. We introduce ClawsBench, a benchmark for evaluating and improving LLM agents in realistic productivity settings. It includes five high-fidelity mock services (Gmail, Slack, Google Calendar, Google Docs, Google Drive) with full state management and deterministic snapshot/restore, along with 44 structured tasks covering single-service, cross-service, and safety-critical scenarios. We decompose agent scaffolding into two independent levers (domain skills that inject API knowledge via progressive disclosure, and a meta prompt that coordinates behavior across services) and vary both to measure their separate and combined effects. Experiments across 6 models, 4 agent harnesses, and 33 conditions show that with full scaffolding, agents achieve task success rates of 39-64% but exhibit unsafe action rates of 7-33%. On OpenClaw, the top five models fall within a 10 percentage-point band on task success (53-63%), with unsafe action rates from 7% to 23% and no consistent ordering between the two metrics. We identify eight recurring patterns of unsafe behavior, including multi-step sandbox escalation and silent contract modification.

Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies. Prior work shows that aligned LLMs encode harmfulness and refusal as separable directions in the residual stream at prompt-side token positions. We show that jailbreaks succeed at prompt encoding by suppressing either the refusal or harmfulness direction before any token is generated, with distinct attack classes occupying separable regions of the harmfulness-refusal plane. Extending the analysis to response-token positions, we find that the model recognizes harmful content while it is generating that content, even when it failed to recognize the input as harmful at the prompt side. Motivated by our findings, we introduce HARC (Harmfulness-And-Refusal Coupling), a fine-tuning method that pairs the two directions across both prompt and response positions. Since the intervention is confined to the harmfulness-refusal subspace, it leaves the rest of the residual stream intact and does not degrade general capability or inflate over-refusal. Across extensive experiments, HARC achieves the strongest robustness-capability-usability trade-off among six baselines spanning the major training-time and inference-time safety methods. The harmfulness and refusal directions at prompt and response positions transfer across the five model families and two scales we tested without architecture-specific tuning.

Computer-use agents (CUAs) that interact with real computer systems can perform automated tasks but face critical safety risks. Ambiguous instructions may trigger harmful actions, and adversarial users can manipulate tool execution to achieve malicious goals. Existing benchmarks mostly focus on short-horizon or GUI-based tasks, evaluating on execution-time errors but overlooking the ability to anticipate planning-time risks. To fill this gap, we present LPS-Bench, a benchmark that evaluates the planning-time safety awareness of MCP-based CUAs under long-horizon tasks, covering both benign and adversarial interactions across 65 scenarios of 7 task domains and 9 risk types. We introduce a multi-agent automated pipeline for scalable data generation and adopt an LLM-as-a-judge evaluation protocol to assess safety awareness through the planning trajectory. Experiments reveal substantial deficiencies in existing CUAs' ability to maintain safe behavior. We further analyze the risks and propose mitigation strategies to improve long-horizon planning safety in MCP-based CUA systems. We open-source our code at https://github.com/tychenn/LPS-Bench.

The rapid development of the AI agent communication protocols, including the Model Context Protocol (MCP), Agent2Agent (A2A), Agora, and Agent Network Protocol (ANP), is reshaping how AI agents communicate with tools, services, and each other. While these protocols support scalable multi-agent interaction and cross-organizational interoperability, their security principles remain understudied, and standardized threat modeling is limited; no protocol-centric risk assessment framework has been established yet. This paper presents a systematic security analysis of four emerging AI agent communication protocols. First, we develop a structured threat modeling analysis that examines protocol architectures, trust assumptions, interaction patterns, and lifecycle behaviors to identify protocol-specific and cross-protocol risk surfaces. Second, we introduce a qualitative risk assessment framework that identifies twelve protocol-level risks and evaluates security posture across the creation, operation, and update phases through systematic assessment of likelihood, impact, and overall protocol risk, with implications for secure deployment and future standardization. Third, we provide a measurement-driven case study on MCP that formalizes the risk of missing mandatory validation/attestation for executable components as a falsifiable security claim by quantifying wrong-provider tool execution under multi-server composition across representative resolver policies. Collectively, our results highlight key design-induced risk surfaces and provide actionable guidance for secure deployment and future standardization of agent communication ecosystems.

Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on defensive refusals. However, in real-world settings, risks also come from non-malicious users seeking help while under psychological distress (e.g., self-harm intentions). In such cases, the model's response can strongly influence the user's next actions. Simple refusals may lead them to repeat, escalate, or move to unsafe platforms, creating worse outcomes. We introduce Constructive Safety Alignment (CSA), a human-centric paradigm that protects against malicious misuse while actively guiding vulnerable users toward safe and helpful results. Implemented in Oyster-I (Oy1), CSA combines game-theoretic anticipation of user reactions, fine-grained risk boundary discovery, and interpretable reasoning control, turning safety into a trust-building process. Oy1 achieves state-of-the-art safety among open models while retaining high general capabilities. On our Constructive Benchmark, it shows strong constructive engagement, close to GPT-5, and unmatched robustness on the Strata-Sword jailbreak dataset, nearing GPT-o1 levels. By shifting from refusal-first to guidance-first safety, CSA redefines the model-user relationship, aiming for systems that are not just safe, but meaningfully helpful. We release Oy1, code, and the benchmark to support responsible, user-centered AI.

While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced integration of core components (attack, defense, and evaluation methods) and an isolation between flexible evaluation frameworks and standardized benchmarking capabilities. These limitations hinder reliable cross-study comparisons and create unnecessary overhead for comprehensive risk assessment. To address these gaps, we present TeleAI-Safety, a modular and reproducible framework coupled with a systematic benchmark for rigorous LLM safety evaluation. Our framework integrates a broad collection of 19 attack methods (including one self-developed method), 29 defense methods, and 19 evaluation methods (including one self-developed method). With a curated attack corpus of 342 samples spanning 12 distinct risk categories, the TeleAI-Safety benchmark conducts extensive evaluations across 14 target models. The results reveal systematic vulnerabilities and model-specific failure cases, highlighting critical trade-offs between safety and utility, and identifying potential defense patterns for future optimization. In practical scenarios, TeleAI-Safety can be flexibly adjusted with customized attack, defense, and evaluation combinations to meet specific demands. We release our complete code and evaluation results to facilitate reproducible research and establish unified safety baselines.

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning traces even when final answers appear safe. We test whether final-answer safety is a sufficient proxy for the full reasoning-answer trajectory by scoring both stages under a unified twenty-principle safety rubric. Using prompts from seven public harmfulness and jailbreak sources, plus four out-of-distribution (OOD) sources, we evaluate 15 open-weight and API-based LRMs across 41K prompts per model. Reasoning traces consistently reveal additional safety risks beyond final answers, especially in high-severity stage-wise failures: leak cases, where unsafe reasoning precedes a safe-looking answer, and escape cases, where benign-looking reasoning precedes an unsafe final response. Principle-level analysis shows that risk concentrates in misinformation, legal compliance, discrimination, physical harm, and psychological harm. We further propose adaptive multi-principle steering, a white-box test-time mitigation that learns one unsafe-to-safe activation direction per safety principle and activates only directions whose current hidden state is closer to the unsafe than safe centroid. On three steerable open reasoning models, adaptive steering reduces unsafe counts in both reasoning traces and final answers on held-out and OOD benchmarks. DeepSeek-R1-Qwen-7B achieves a 40.8% average unsafe-count reduction while retaining 97.7% macro-averaged accuracy on BBH, GSM8K, and MMLU. These results suggest that LRM safety should be evaluated and mitigated over the full exposed reasoning-answer trajectory, not only at the final-answer stage.

This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a state in which they continuously generate harmful content while executing otherwise benign tasks. We introduce TVD (Task, Validator, Data), a framework that triggers ISC through domain tasks where generating harmful content is the only valid completion, and construct ISC-Bench containing 53 scenarios across 8 professional disciplines. Evaluated on JailbreakBench, three representative scenarios yield worst-case safety failure rates averaging 95.3% across four frontier LLMs (including GPT-5.2 and Claude Sonnet 4.5), substantially exceeding standard jailbreak attacks. Frontier models are more vulnerable than earlier LLMs: the very capabilities that enable complex task execution become liabilities when tasks intrinsically involve harmful content. This reveals a growing attack surface: almost every professional domain uses tools that process sensitive data, and each new dual-use tool automatically expands this vulnerability--even without any deliberate attack. Despite substantial alignment efforts, frontier LLMs retain inherently unsafe internal capabilities: alignment reshapes observable outputs but does not eliminate the underlying risk profile. These findings underscore the need for caution when deploying LLMs in high-stakes settings. Source code: https://github.com/wuyoscar/ISC-Bench

Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes essential. Existing adversarial attacks, however, have notable limitations. Prompt-based jailbreaks rely on heuristic search and transfer poorly, model intervention methods require privileged access to internal representations, and optimization-based input attacks remain output-centric and are fundamentally limited to MoE models due to the non-differentiable routing mechanism. In this paper, we present RouteHijack, a routing-aware jailbreak for MoE LLMs. Our key insight is that safety behavior is concentrated in a small subset of experts, creating an opportunity to steer model behavior by influencing routing decisions through input optimization. Building on this observation, RouteHijack first performs response-driven expert localization to identify safety-critical and harmful experts by contrasting activations under safe refusals and harmful completions. It then constructs adversarial suffixes with a routing-aware objective that suppresses safety experts, promotes harmful experts, and prevents early-stage refusal during generation. At inference time, the optimized suffix is appended to a malicious prompt, requiring only input access. Across seven MoE LLMs, RouteHijack achieves a 69.3\% average attack success rate (ASR), outperforming prior optimization-based attack by 3.2times. RouteHijack also transfers zero-shot across five sibling MoE variants, raising average ASR from 27.7\% to 61.2\%, and further generalizes to three MoE-based VLMs, increasing average ASR from 2.47\% to 38.7\%. These findings expose a fundamental vulnerability in sparse expert architectures and highlight the need for defenses beyond output-level alignment.

Vision-Language-Action (VLA) models inherit rich world knowledge from vision-language backbones and acquire executable skills via action demonstrations. However, existing evaluations largely focus on action execution success, leaving action policies loosely coupled with visual-linguistic semantics. This decoupling exposes a systematic vulnerability whereby correct action execution may induce unsafe outcomes under semantic risk. To expose this vulnerability, we introduce HazardArena, a benchmark designed to evaluate semantic safety in VLAs under controlled yet risk-bearing contexts. HazardArena is constructed from safe/unsafe twin scenarios that share matched objects, layouts, and action requirements, differing only in the semantic context that determines whether an action is unsafe. We find that VLA models trained exclusively on safe scenarios often fail to behave safely when evaluated in their corresponding unsafe counterparts. HazardArena includes over 2,000 assets and 40 risk-sensitive tasks spanning 7 real-world risk categories grounded in established robotic safety standards. To mitigate this vulnerability, we propose a training-free Safety Option Layer that constrains action execution using semantic attributes or a vision-language judge, substantially reducing unsafe behaviors with minimal impact on task performance. We hope that HazardArena highlights the need to rethink how semantic safety is evaluated and enforced in VLAs as they scale toward real-world deployment.

Tool-using automation systems, from scripts and CI bots to agentic assistants, fail in recurring patterns. Common failures include unsafe side effects, invalid arguments, uncontrolled retries, and leakage of sensitive outputs. Many mitigations are model-centric and prompt-dependent, so they are brittle and do not generalize to non-LLM callers. We present Policy-First Tooling, a model-agnostic permission layer that mediates tool invocation through explicit constraints, risk-aware gating, recovery controls, and auditable explanations. The paper contributes a compact policy DSL, a runtime enforcement architecture with actionable rationale and fix hints, and a reproducible benchmark based on trace replay with controlled fault and misuse injection. In 225 controlled runs across five policy packs and three fault profiles, stricter packs improve violation prevention from 0.000 in P0 to 0.681 in P4, while task success drops from 0.356 to 0.067. Retry amplification decreases from 3.774 in P0 to 1.378 in P4, and leakage recall reaches 0.875 under injected secret outputs. These results make safety to utility trade-offs explicit and measurable.

Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step workflows, while public blockchains have evolved into a programmable substrate for value transfer, access control, and verifiable state transitions. Their convergence introduces a high-stakes systems challenge: designing standard, interoperable, and secure interfaces that allow agents to observe on-chain state, formulate transaction intents, and authorize execution without exposing users, protocols, or organizations to unacceptable security, governance, or economic risks. This survey systematizes the emerging landscape of agent-blockchain interoperability through a systematic literature review, identifying 317 relevant works from an initial pool of over 3000 records. We contribute a five-part taxonomy of integration patterns spanning read-only analytics, simulation and intent generation, delegated execution, autonomous signing, and multi-agent workflows; a threat model tailored to agent-driven transaction pipelines that captures risks ranging from prompt injection and policy misuse to key compromise, adversarial execution dynamics, and multi-agent collusion; and a comparative capability matrix analyzing more than 20 representative systems across 13 dimensions, including custody models, permissioning, policy enforcement, observability, and recovery. Building on the gaps revealed by this analysis, we outline a research roadmap centered on two interface abstractions: a Transaction Intent Schema for portable and unambiguous goal specification, and a Policy Decision Record for auditable, verifiable policy enforcement across execution environments. We conclude by proposing a reproducible evaluation suite and benchmarks for assessing the safety, reliability, and economic robustness of agent-mediated on-chain execution.

OpenClaw-style agent stacks turn language into privileged execution: LLM intents flow through tool interception, policy gates, and a local executor. In parallel, skill marketplaces such as skills.sh make capability acquisition as easy as installing skills and CLIs, creating a growing capability supply chain. Together, these trends shift the dominant safety failure mode from "wrong answers" to execution-induced loss, where untrusted prompts, compromised skills, or narrative manipulation can trigger real trades and irreversible side effects. We propose Survivability-Aware Execution (SAE), an execution-layer survivability standard for OpenClaw-style systems and skill-enabled agents. SAE sits as middleware between a strategy engine (LLM or non-LLM) and the exchange executor. It defines an explicit execution contract (ExecutionRequest, ExecutionContext, ExecutionDecision) and enforces non-bypassable last-mile invariants: projection-based exposure budgets, cooldown and order-rate limits, slippage bounds, staged execution, and tool/venue allowlists. To make delegated execution testable under supply-chain risk, we operationalize the Delegation Gap (DG) via a logged Intended Policy Spec that enables deterministic out-of-scope labeling and reproducible DG metrics. On an offline replay using official Binance USD-M BTCUSDT/ETHUSDT perpetual data (15m; 2025-09-01--2025-12-01, incl. funding), SAE improves survivability: MDD drops from 0.4643 to 0.0319 (Full; 93.1%), |CVaR_0.99| shrinks from 4.025e-3 to ~1.02e-4 (~97.5%), and DG loss proxy falls from 0.647 to 0.019 (~97.0%). AttackSuccess decreases from 1.00 to 0.728 with zero FalseBlock in this run. Block bootstrap, paired Wilcoxon, and two-proportion tests confirm the shifts. SAE reframes agentic trading safety for the OpenClaw+skills era: treat upstream intent and skills as untrusted, and enforce survivability where actions become side effects.

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.

The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security analysis of the protocol specification exists. We present the first rigorous security analysis of MCP's architectural design, identifying three fundamental protocol-level vulnerabilities: (1) absence of capability attestation allowing servers to claim arbitrary permissions, (2) bidirectional sampling without origin authentication enabling server-side prompt injection, and (3) implicit trust propagation in multi-server configurations. We implement MCPBench, a novel framework bridging existing agent security benchmarks to MCP-compliant infrastructure, enabling direct measurement of protocol-specific attack surfaces. Through controlled experiments on 847 attack scenarios across five MCP server implementations, we demonstrate that MCP's architectural choices amplify attack success rates by 23--41\% compared to equivalent non-MCP integrations. We propose MCPSec, a backward-compatible protocol extension adding capability attestation and message authentication, reducing attack success rates from 52.8\% to 12.4\% with median latency overhead of 8.3ms per message. Our findings establish that MCP's security weaknesses are architectural rather than implementation-specific, requiring protocol-level remediation.

The o1 system card identifies the o1 models as the most robust within OpenAI, with their defining characteristic being the progression from rapid, intuitive thinking to slower, more deliberate reasoning. This observation motivated us to investigate the influence of System-2 thinking patterns on model safety. In our preliminary research, we conducted safety evaluations of the o1 model, including complex jailbreak attack scenarios using adversarial natural language prompts and mathematical encoding prompts. Our findings indicate that the o1 model demonstrates relatively improved safety performance; however, it still exhibits vulnerabilities, particularly against jailbreak attacks employing mathematical encoding. Through detailed case analysis, we identified specific patterns in the o1 model's responses. We also explored the alignment of System-2 safety in open-source models using prompt engineering and supervised fine-tuning techniques. Experimental results show that some simple methods to encourage the model to carefully scrutinize user requests are beneficial for model safety. Additionally, we proposed a implementation plan for process supervision to enhance safety alignment. The implementation details and experimental results will be provided in future versions.

The past year has seen rapid acceleration in the development of large language models (LLMs). However, without proper steering and safeguards, LLMs will readily follow malicious instructions, provide unsafe advice, and generate toxic content. We introduce SimpleSafetyTests (SST) as a new test suite for rapidly and systematically identifying such critical safety risks. The test suite comprises 100 test prompts across five harm areas that LLMs, for the vast majority of applications, should refuse to comply with. We test 11 open-access and open-source LLMs and four closed-source LLMs, and find critical safety weaknesses. While some of the models do not give a single unsafe response, most give unsafe responses to more than 20% of the prompts, with over 50% unsafe responses in the extreme. Prepending a safety-emphasising system prompt substantially reduces the occurrence of unsafe responses, but does not completely stop them from happening. Trained annotators labelled every model response to SST (n = 3,000). We use these annotations to evaluate five AI safety filters (which assess whether a models' response is unsafe given a prompt) as a way of automatically evaluating models' performance on SST. The filters' performance varies considerably. There are also differences across the five harm areas, and on the unsafe versus safe responses. The widely-used Perspective API has 72% accuracy and a newly-created zero-shot prompt to OpenAI's GPT-4 performs best with 89% accuracy. Content Warning: This paper contains prompts and responses that relate to child abuse, suicide, self-harm and eating disorders, scams and fraud, illegal items, and physical harm.

Search agents connect LLMs to the Internet, enabling access to broader and more up-to-date information. However, unreliable search results may also pose safety threats to end users, establishing a new threat surface. In this work, we conduct two in-the-wild experiments to demonstrate both the prevalence of low-quality search results and their potential to misguide agent behaviors. To counter this threat, we introduce an automated red-teaming framework that is systematic, scalable, and cost-efficient, enabling lightweight and harmless safety assessments of search agents. Building on this framework, we construct the SafeSearch benchmark, which includes 300 test cases covering five categories of risks (e.g., misinformation and indirect prompt injection). Using this benchmark, we evaluate three representative search agent scaffolds, covering search workflow, tool-calling, and deep research, across 7 proprietary and 8 open-source backend LLMs. Our results reveal substantial vulnerabilities of LLM-based search agents: when exposed to unreliable websites, the highest ASR reached 90.5% for GPT-4.1-mini under a search workflow setting. Moreover, our analysis highlights the limited effectiveness of common defense practices, such as reminder prompting. This emphasizes the value of our framework in promoting transparency for safer agent development. Our codebase and test cases are publicly available: https://github.com/jianshuod/SafeSearch.

Distributed protocols should be robust to both benign malfunction (e.g. packet loss or delay) and attacks (e.g. message replay) from internal or external adversaries. In this paper we take a formal approach to the automated synthesis of attackers, i.e. adversarial processes that can cause the protocol to malfunction. Specifically, given a formal threat model capturing the distributed protocol model and network topology, as well as the placement, goals, and interface (inputs and outputs) of potential attackers, we automatically synthesize an attacker. We formalize four attacker synthesis problems - across attackers that always succeed versus those that sometimes fail, and attackers that attack forever versus those that do not - and we propose algorithmic solutions to two of them. We report on a prototype implementation called KORG and its application to TCP as a case-study. Our experiments show that KORG can automatically generate well-known attacks for TCP within seconds or minutes.

Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detailed reports. However, the misuse of LLMs with such powerful capabilities can lead to even greater risks. This is especially concerning in high-stakes and knowledge-intensive domains such as biosecurity, where DR can generate a professional report containing detailed forbidden knowledge. Unfortunately, we have found such risks in practice: simply submitting a harmful query, which a standalone LLM directly rejects, can elicit a detailed and dangerous report from DR agents. This highlights the elevated risks and underscores the need for a deeper safety analysis. Yet, jailbreak methods designed for LLMs fall short in exposing such unique risks, as they do not target the research ability of DR agents. To address this gap, we propose two novel jailbreak strategies: Plan Injection, which injects malicious sub-goals into the agent's plan; and Intent Hijack, which reframes harmful queries as academic research questions. We conducted extensive experiments across different LLMs and various safety benchmarks, including general and biosecurity forbidden prompts. These experiments reveal 3 key findings: (1) Alignment of the LLMs often fail in DR agents, where harmful prompts framed in academic terms can hijack agent intent; (2) Multi-step planning and execution weaken the alignment, revealing systemic vulnerabilities that prompt-level safeguards cannot address; (3) DR agents not only bypass refusals but also produce more coherent, professional, and dangerous content, compared with standalone LLMs. These results demonstrate a fundamental misalignment in DR agents and call for better alignment techniques tailored to DR agents. Code and datasets are available at https://chenxshuo.github.io/deeper-harm.

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond conventional text-level jailbreaks, yet existing safety evaluations fall short: most test models in isolated chat settings, rely on synthetic environments, and do not account for how the agent framework itself shapes safety outcomes. We introduce CLAWSAFETY, a benchmark of 120 adversarial test scenarios organized along three dimensions (harm domain, attack vector, and harmful action type) and grounded in realistic, high-privilege professional workspaces spanning software engineering, finance, healthcare, law, and DevOps. Each test case embeds adversarial content in one of three channels the agent encounters during normal work: workspace skill files, emails from trusted senders, and web pages. We evaluate five frontier LLMs as agent backbones, running 2,520 sandboxed trials across all configurations. Attack success rates (ASR) range from 40\% to 75\% across models and vary sharply by injection vector, with skill instructions (highest trust) consistently more dangerous than email or web content. Action-trace analysis reveals that the strongest model maintains hard boundaries against credential forwarding and destructive actions, while weaker models permit both. Cross-scaffold experiments on three agent frameworks further demonstrate that safety is not determined by the backbone model alone but depends on the full deployment stack, calling for safety evaluation that treats model and framework as joint variables. Code and data will be available at: https://weibowen555.github.io/ClawSafety/.

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of intrinsic risk, where intrinsic failures remain latent, propagate across long-horizon execution, and eventually lead to high-consequence outcomes. To evaluate this setting, we introduce non-attack intrinsic risk auditing and present HINTBench, a benchmark of 629 agent trajectories (523 risky, 106 safe; 33 steps on average) supporting three tasks: risk detection, risk-step localization, and intrinsic failure-type identification. Its annotations are organized under a unified five-constraint taxonomy. Experiments reveal a substantial capability gap: strong LLMs perform well on trajectory-level risk detection, but their performance drops to below 35 Strict-F1 on risk-step localization, while fine-grained failure diagnosis proves even harder. Existing guard models transfer poorly to this setting. These findings establish intrinsic risk auditing as an open challenge for agent safety.

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this issue, we propose a method named IRR (Identify, Remove, and Recalibrate for Safety Realignment) that performs safety realignment for LLMs. The core of IRR is to identify and remove unsafe delta parameters from the fine-tuned models, while recalibrating the retained ones. We evaluate the effectiveness of IRR across various datasets, including both full fine-tuning and LoRA methods. Our results demonstrate that IRR significantly enhances the safety performance of fine-tuned models on safety benchmarks, such as harmful queries and jailbreak attacks, while maintaining their performance on downstream tasks. The source code is available at: https://anonymous.4open.science/r/IRR-BD4F.

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks remain fragile, lacking principled mechanisms for secure information flow, reliability, and multi-agent coordination. In this work, we introduce SAFEFLOW, a new protocol-level framework for building trustworthy LLM/VLM-based agents. SAFEFLOW enforces fine-grained information flow control (IFC), precisely tracking provenance, integrity, and confidentiality of all the data exchanged between agents, tools, users, and environments. By constraining LLM reasoning to respect these security labels, SAFEFLOW prevents untrusted or adversarial inputs from contaminating high-integrity decisions. To ensure robustness in concurrent multi-agent settings, SAFEFLOW introduces transactional execution, conflict resolution, and secure scheduling over shared state, preserving global consistency across agents. We further introduce mechanisms, including write-ahead logging, rollback, and secure caches, that further enhance resilience against runtime errors and policy violations. To validate the performances, we built SAFEFLOWBENCH, a comprehensive benchmark suite designed to evaluate agent reliability under adversarial, noisy, and concurrent operational conditions. Extensive experiments demonstrate that agents built with SAFEFLOW maintain impressive task performance and security guarantees even in hostile environments, substantially outperforming state-of-the-art. Together, SAFEFLOW and SAFEFLOWBENCH lay the groundwork for principled, robust, and secure agent ecosystems, advancing the frontier of reliable autonomy.

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.

LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, the first benchmark to focus on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories -- misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realistic misuses of web agents. We evaluate leading LLM-based web agents, including GPT-4o, Claude-3.5 Sonnet, Qwen-2-VL 72B, and Llama-3.2 90B, on our benchmark. To systematically assess their susceptibility to harmful tasks, we introduce the Agent Risk Assessment framework that categorizes agent behavior across four risk levels. We find agents are surprisingly compliant with malicious requests, with GPT-4o and Qwen-2 completing 34.7% and 27.3% of harmful requests, respectively. Our findings highlight the urgent need for safety alignment procedures for web agents. Our benchmark is available here: https://safearena.github.io

Public LLMs such as the Llama 2-Chat have driven huge activity in LLM research. These models underwent alignment training and were considered safe. Recently Qi et al. (2023) reported that even benign fine-tuning (e.g., on seemingly safe datasets) can give rise to unsafe behaviors in the models. The current paper is about methods and best practices to mitigate such loss of alignment. Through extensive experiments on several chat models (Meta's Llama 2-Chat, Mistral AI's Mistral 7B Instruct v0.2, and OpenAI's GPT-3.5 Turbo), this paper uncovers that the prompt templates used during fine-tuning and inference play a crucial role in preserving safety alignment, and proposes the "Pure Tuning, Safe Testing" (PTST) principle -- fine-tune models without a safety prompt, but include it at test time. Fine-tuning experiments on GSM8K, ChatDoctor, and OpenOrca show that PTST significantly reduces the rise of unsafe behaviors, and even almost eliminates them in some cases.

Alignment tuning is meant to make harmful-request refusal robust, yet this safety behavior can be erased by a small set of benign fine-tuning examples. This is a deployment risk for open-weight models because a checkpoint can pass refusal tests at release time and later lose refusal under low-cost downstream fine-tuning. Prior work has established these refusal failures, but existing studies do not show how to detect this fragility in the aligned model itself before an attack or fine-tuning intervention is run. We introduce Skin-Deep, a geometric diagnostic that detects alignment fragility directly from the aligned model's hidden-state activations before such an intervention is run and compresses the layer-wise safety geometry into a single scalar, the Geometric Fragility Score (GFS). Applied to twenty-one instruction-tuned models spanning six alignment recipes and 3B--32B parameters, Skin-Deep reveals a recurring low-rank safety subspace across model families. Direction ablations show that removing directions in this subspace weakens harmful-request refusal, providing causal evidence that the recovered geometry underlies refusal behavior. Crucially, GFS identifies, before any fine-tuning, the initially safe model that retains the most refusal after small-scale LoRA fine-tuning. These results establish GFS as a practical pre-deployment diagnostic for flagging fragile refusal behavior without running an attack.

As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level cybersecurity threats, fundamentally different from prompt-based vulnerabilities. To systematically evaluate these interpreter-specific risks, we propose CIRCLE (Code-Interpreter Resilience Check for LLM Exploits), a simple benchmark comprising 1,260 prompts targeting CPU, memory, and disk resource exhaustion. Each risk category includes explicitly malicious ("direct") and plausibly benign ("indirect") prompt variants. Our automated evaluation framework assesses not only whether LLMs refuse or generates risky code, but also executes the generated code within the interpreter environment to evaluate code correctness, simplifications made by the LLM to make the code safe, or execution timeouts. Evaluating 7 commercially available models from OpenAI and Google, we uncover significant and inconsistent vulnerabilities. For instance, evaluations show substantial disparities even within providers - OpenAI's o4-mini correctly refuses risky requests at 7.1%, notably higher rates compared to GPT-4.1 at 0.5%. Results particularly underscore that indirect, socially-engineered prompts substantially weaken model defenses. This highlights an urgent need for interpreter-specific cybersecurity benchmarks, dedicated mitigation tools (e.g., guardrails), and clear industry standards to guide safe and responsible deployment of LLM interpreter integrations. The benchmark dataset and evaluation code are publicly released to foster further research.

Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce new security risks in high-stakes and highly regulated financial environments. However, existing safety evaluations largely focus on language-model-level content compliance or abstract agent settings, failing to capture execution-grounded risks arising from real operational workflows and state-changing actions. To bridge this gap, we propose FinVault, the first execution-grounded security benchmark for financial agents, comprising 31 regulatory case-driven sandbox scenarios with state-writable databases and explicit compliance constraints, together with 107 real-world vulnerabilities and 963 test cases that systematically cover prompt injection, jailbreaking, financially adapted attacks, as well as benign inputs for false-positive evaluation. Experimental results reveal that existing defense mechanisms remain ineffective in realistic financial agent settings, with average attack success rates (ASR) still reaching up to 50.0\% on state-of-the-art models and remaining non-negligible even for the most robust systems (ASR 6.7\%), highlighting the limited transferability of current safety designs and the need for stronger financial-specific defenses. Our code can be found at https://github.com/aifinlab/FinVault.

LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses unauthorized resources or leaks context to the wrong agent. Output-level evaluation cannot see these failures, yet most safety benchmarks score only final outputs or terminal states, even though many violations occur mid-trajectory rather than at termination. The central question is whether the harness respects user intent, permission boundaries, and information-flow constraints throughout execution. To address this gap, we propose HarnessAudit, a framework that audits full execution trajectories across boundary compliance, execution fidelity, and system stability, with a focus on multi-agent harnesses where these risks are most pronounced. We further introduce HarnessAudit-Bench, a benchmark of 210 tasks across eight real-world domains, instantiated in both single-agent and multi-agent configurations with embedded safety constraints. Evaluating ten harness configurations across frontier models and three multi-agent frameworks, we find that: (i) task completion is misaligned with safe execution, and violations accumulate with trajectory length; (ii) safety risks vary across domains, task types, and agent roles; (iii) most violations concentrate in resource access and inter-agent information transfer; and (iv) multi-agent collaboration expands the safety risk surface, while harness design sets the upper bound of safe deployment.

Deploying language models (LMs) necessitates outputs to be both high-quality and compliant with safety guidelines. Although Inference-Time Guardrails (ITG) offer solutions that shift model output distributions towards compliance, we find that current methods struggle in balancing safety with helpfulness. ITG Methods that safely address non-compliant queries exhibit lower helpfulness while those that prioritize helpfulness compromise on safety. We refer to this trade-off as the guardrail tax, analogous to the alignment tax. To address this, we propose PrimeGuard, a novel ITG method that utilizes structured control flow. PrimeGuard routes requests to different self-instantiations of the LM with varying instructions, leveraging its inherent instruction-following capabilities and in-context learning. Our tuning-free approach dynamically compiles system-designer guidelines for each query. We construct and release safe-eval, a diverse red-team safety benchmark. Extensive evaluations demonstrate that PrimeGuard, without fine-tuning, overcomes the guardrail tax by (1) significantly increasing resistance to iterative jailbreak attacks and (2) achieving state-of-the-art results in safety guardrailing while (3) matching helpfulness scores of alignment-tuned models. Extensive evaluations demonstrate that PrimeGuard, without fine-tuning, outperforms all competing baselines and overcomes the guardrail tax by improving the fraction of safe responses from 61% to 97% and increasing average helpfulness scores from 4.17 to 4.29 on the largest models, while reducing attack success rate from 100% to 8%. PrimeGuard implementation is available at https://github.com/dynamofl/PrimeGuard and safe-eval dataset is available at https://huggingface.co/datasets/dynamoai/safe_eval.

Given the growing concerns around the safety and risks of Large Language Models (LLMs), it is essential to develop methods for mitigating these issues. We introduce Safe and Responsible Large Language Model (SR_{LLM}) , a model designed to enhance the safety of language generation using LLMs. Our approach incorporates a comprehensive LLM safety risk taxonomy and utilizes a dataset annotated by experts that align with this taxonomy. SR_{LLM} is designed to identify potentially unsafe content and produce benign variations. It employs instruction-based and parameter-efficient fine-tuning methods, making the model not only effective in enhancing safety but also resource-efficient and straightforward to adjust. Through our testing on five benchmark datasets and two proprietary datasets, we observed notable reductions in the generation of unsafe content. Moreover, following the implementation of safety measures, there was a significant improvement in the production of safe content. We detail our fine-tuning processes and how we benchmark safety for SR_{LLM} with the community engagement and promote the responsible advancement of LLMs. All the data and code are available anonymous at https://github.com/shainarazavi/Safe-Responsible-LLM .

The development of large language models (LLMs) has entered in a experience-driven era, flagged by the emergence of environment feedback-driven learning via reinforcement learning and tool-using agents. This encourages the emergenece of model context protocol (MCP), which defines the standard on how should a LLM interact with external services, such as \api and data. However, as MCP becomes the de facto standard for LLM agent systems, it also introduces new safety risks. In particular, MCP introduces third-party services, which are not controlled by the LLM developers, into the agent systems. These third-party MCP services provider are potentially malicious and have the economic incentives to exploit vulnerabilities and sabotage user-agent interactions. In this position paper, we advocate the research community in LLM safety to pay close attention to the new safety risks issues introduced by MCP, and develop new techniques to build safe MCP-powered agent systems. To establish our position, we argue with three key parts. (1) We first construct \framework, a controlled framework to examine safety issues in MCP-powered agent systems. (2) We then conduct a series of pilot experiments to demonstrate the safety risks in MCP-powered agent systems is a real threat and its defense is not trivial. (3) Finally, we give our outlook by showing a roadmap to build safe MCP-powered agent systems. In particular, we would call for researchers to persue the following research directions: red teaming, MCP safe LLM development, MCP safety evaluation, MCP safety data accumulation, MCP service safeguard, and MCP safe ecosystem construction. We hope this position paper can raise the awareness of the research community in MCP safety and encourage more researchers to join this important research direction. Our code is available at https://github.com/littlelittlenine/SafeMCP.git.

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom datasets also encourage this practice. But, what are the safety costs associated with such custom fine-tuning? We note that while existing safety alignment infrastructures can restrict harmful behaviors of LLMs at inference time, they do not cover safety risks when fine-tuning privileges are extended to end-users. Our red teaming studies find that the safety alignment of LLMs can be compromised by fine-tuning with only a few adversarially designed training examples. For instance, we jailbreak GPT-3.5 Turbo's safety guardrails by fine-tuning it on only 10 such examples at a cost of less than $0.20 via OpenAI's APIs, making the model responsive to nearly any harmful instructions. Disconcertingly, our research also reveals that, even without malicious intent, simply fine-tuning with benign and commonly used datasets can also inadvertently degrade the safety alignment of LLMs, though to a lesser extent. These findings suggest that fine-tuning aligned LLMs introduces new safety risks that current safety infrastructures fall short of addressing -- even if a model's initial safety alignment is impeccable, it is not necessarily to be maintained after custom fine-tuning. We outline and critically analyze potential mitigations and advocate for further research efforts toward reinforcing safety protocols for the custom fine-tuning of aligned LLMs.

Large foundation models are integrated into Computer Use Agents (CUAs), enabling autonomous interaction with operating systems through graphical user interfaces (GUIs) to perform complex tasks. This autonomy introduces serious security risks: malicious instructions or visual prompt injections can trigger unsafe reasoning and cause harmful system-level actions. Existing defenses, such as detection-based blocking, prevent damage but often abort tasks prematurely, reducing agent utility. In this paper, we present MirrorGuard, a plug-and-play defense framework that uses simulation-based training to improve CUA security in the real world. To reduce the cost of large-scale training in operating systems, we propose a novel neural-symbolic simulation pipeline, which generates realistic, high-risk GUI interaction trajectories entirely in a text-based simulated environment, which captures unsafe reasoning patterns and potential system hazards without executing real operations. In the simulation environment, MirrorGuard learns to intercept and rectify insecure reasoning chains of CUAs before they produce and execute unsafe actions. In real-world testing, extensive evaluations across diverse benchmarks and CUA architectures show that MirrorGuard significantly mitigates security risks. For instance, on the ByteDance UI-TARS system, it reduces the unsafe rate from 66.5% to 13.0% while maintaining a marginal false refusal rate (FRR). In contrast, the state-of-the-art GuardAgent only achieves a reduction to 53.9% and suffers from a 15.4% higher FRR. Our work proves that simulation-derived defenses can provide robust, real-world protection while maintaining the fundamental utility of the agent. Our code and model are publicly available at https://bmz-q-q.github.io/MirrorGuard/.

Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns -- fine-tuning over a few harmful data uploaded by the users can compromise the safety alignment of the model. The attack, known as harmful fine-tuning, has raised a broad research interest among the community. However, as the attack is still new, we observe from our miserable submission experience that there are general misunderstandings within the research community. We in this paper aim to clear some common concerns for the attack setting, and formally establish the research problem. Specifically, we first present the threat model of the problem, and introduce the harmful fine-tuning attack and its variants. Then we systematically survey the existing literature on attacks/defenses/mechanical analysis of the problem. Finally, we outline future research directions that might contribute to the development of the field. Additionally, we present a list of questions of interest, which might be useful to refer to when reviewers in the peer review process question the realism of the experiment/attack/defense setting. A curated list of relevant papers is maintained and made accessible at: https://github.com/git-disl/awesome_LLM-harmful-fine-tuning-papers.

Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools. Existing approaches mainly optimize attack success and preserve artifacts such as benchmarks, payloads, or attack programs, which record where attacks succeed but not the enabling conditions behind unsafe agent behavior. We study automated red-teaming for production LLM agents using one agentic research environment to discover reusable vulnerability knowledge about another. We present AHA, a falsifiable discovery loop that proposes a vulnerability hypothesis, constructs a falsifier, instantiates a valid attack, executes it in a sandboxed harness, reflects on the trajectory, and promotes confirmed findings into a Vulnerability Concept Graph (VCG). Each concept links an attacker-facing surface to an unsafe trajectory through a claim, enabling condition, falsifier, transfer prediction, and supporting evidence. Across Claude Code and Codex on three scenarios covering direct and indirect attacks, the discovered concepts reveal a reusable vulnerability core across models and agents. A frozen VCG requires no further search and outperforms the strongest frozen discovery baseline by 14.2 percentage points under the same single-shot protocol, while transferring across scenarios and attack channels. The resulting VCG provides an auditable artifact for production safety teams to inspect vulnerabilities, validate patches, and accumulate reusable safety knowledge. Our code is available at https://github.com/henrymao2004/Auto-research-red-teaming-in-sleep.

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an architecture-centric security evaluation that defines 14 trust-boundary attack classes spanning planning, memory, retrieval, tool use, and delegation, and detects failures via *trace-auditable conversation breaks* (unauthorized or unsafe tool use, wrong-principal actions, state/objective integrity violations, and attack-linked deviations). Holding the base model fixed, we evaluate eight agent archetypes under persistent multi-turn interaction and observe substantial architectural variation in mean security break rate (MSBR), ranging from 0.29 pm 0.04 (LangGraph) to 0.51 pm 0.07 (AutoGPT). The highest-risk classes are operational: Denial-of-Wallet (0.62 pm 0.08), Authorization Confusion (0.54 pm 0.10), Retrieval Poisoning (0.47 pm 0.09), and Planning Manipulation (0.44 pm 0.11), while prompt-centric classes remain below 0.20 under standard settings. Breaks are dominated by boundary violations (SIV 31%, WPA 27%, UTI+UTA 24%, ATD 18%), and authorization confusion correlates with objective and tool hijacking (ρapprox 0.63 and ρapprox 0.58). AgentFence reframes agent security around what matters operationally: whether an agent stays within its goal and authority envelope over time.

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not well understood. In this study, we show that RL-trained search models inherit refusal from instruction tuning and often deflect harmful requests by turning them into safe queries. However, this safety is fragile. Two simple attacks, one that forces the model to begin response with search (Search attack), another that encourages models to repeatedly search (Multi-search attack), trigger cascades of harmful searches and answers. Across two model families (Qwen, Llama) with both local and web search, these attacks lower refusal rates by up to 60.0%, answer safety by 82.5%, and search-query safety by 82.4%. The attacks succeed by triggering models to generate harmful, request-mirroring search queries before they can generate the inherited refusal tokens. This exposes a core weakness of current RL training: it rewards continued generation of effective queries without accounting for their harmfulness. As a result, RL search models have vulnerabilities that users can easily exploit, making it urgent to develop safety-aware agentic RL pipelines optimising for safe search.

Despite the remarkable versatility of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) to generalize across both language and vision tasks, LLMs and MLLMs have shown vulnerability to jailbreaking, generating textual outputs that undermine safety, ethical, and bias standards when exposed to harmful or sensitive inputs. With the recent advancement of safety alignment via preference-tuning from human feedback, LLMs and MLLMs have been equipped with safety guardrails to yield safe, ethical, and fair responses with regard to harmful inputs. However, despite the significance of safety alignment, research on the vulnerabilities remains largely underexplored. In this paper, we investigate the unexplored vulnerability of the safety alignment, examining its ability to consistently provide safety guarantees for out-of-distribution(OOD)-ifying harmful inputs that may fall outside the aligned data distribution. Our key observation is that OOD-ifying the vanilla harmful inputs highly increases the uncertainty of the model to discern the malicious intent within the input, leading to a higher chance of being jailbroken. Exploiting this vulnerability, we propose JOOD, a new Jailbreak framework via OOD-ifying inputs beyond the safety alignment. We explore various off-the-shelf visual and textual transformation techniques for OOD-ifying the harmful inputs. Notably, we observe that even simple mixing-based techniques such as image mixup prove highly effective in increasing the uncertainty of the model, thereby facilitating the bypass of the safety alignment. Experiments across diverse jailbreak scenarios demonstrate that JOOD effectively jailbreaks recent proprietary LLMs and MLLMs such as GPT-4 and o1 with high attack success rate, which previous attack approaches have consistently struggled to jailbreak. Code is available at https://github.com/naver-ai/JOOD.

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and creative forms of adversarial prompting, including manually generated test cases. In this work, we present two new test cases in mental health for (i) suicide and (ii) self-harm, using multi-step, prompt-level jailbreaking and bypass built-in content and safety filters. We show that user intent is disregarded, leading to the generation of detailed harmful content and instructions that could cause real-world harm. We conduct an empirical evaluation across six widely available LLMs, demonstrating the generalizability and reliability of the bypass. We assess these findings and the multilayered ethical tensions that they present for their implications on prompt-response filtering and context- and task-specific model development. We recommend a more comprehensive and systematic approach to AI safety and ethics while emphasizing the need for continuous adversarial testing in safety-critical AI deployments. We also argue that while certain clearly defined safety measures and guardrails can and must be implemented in LLMs, ensuring robust and comprehensive safety across all use cases and domains remains extremely challenging given the current technical maturity of general-purpose LLMs.

Large language models (LLMs) are increasingly deployed in medical contexts, raising critical concerns about safety, alignment, and susceptibility to adversarial manipulation. While prior benchmarks assess model refusal capabilities for harmful prompts, they often lack clinical specificity, graded harmfulness levels, and coverage of jailbreak-style attacks. We introduce CARES (Clinical Adversarial Robustness and Evaluation of Safety), a benchmark for evaluating LLM safety in healthcare. CARES includes over 18,000 prompts spanning eight medical safety principles, four harm levels, and four prompting styles: direct, indirect, obfuscated, and role-play, to simulate both malicious and benign use cases. We propose a three-way response evaluation protocol (Accept, Caution, Refuse) and a fine-grained Safety Score metric to assess model behavior. Our analysis reveals that many state-of-the-art LLMs remain vulnerable to jailbreaks that subtly rephrase harmful prompts, while also over-refusing safe but atypically phrased queries. Finally, we propose a mitigation strategy using a lightweight classifier to detect jailbreak attempts and steer models toward safer behavior via reminder-based conditioning. CARES provides a rigorous framework for testing and improving medical LLM safety under adversarial and ambiguous conditions.

Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat assistants, unsafe content in these agents can propagate through persistent state, reusable skills, and tool-mediated interactions, creating a substantially larger semantic attack surface. We observe that most security-critical interactions in such agents are transmitted through natural-language token flows, including memory updates, tool arguments, retrieved files, and inter-component communications. This observation enables a new security formulation: unsafe behavior can be intercepted as risky semantic flows before reaching privileged runtime sinks. Based on this insight, we propose TokenWall, a runtime defense framework that acts as a semantic firewall over agent token flows. TokenWall performs boundary-aware semantic auditing over these flows, constructing structured source-sink audit records, applying lightweight local inspection before execution, and selectively escalating ambiguous high-risk cases to stronger arbitration modules. Unlike prior approaches that rely on sparse auditing or remote large-model oversight, TokenWall enables full-coverage pre-execution mediation while reducing remote arbitration and latency. Experiments on CIK-Bench show that TokenWall reduces attack success rate to 12.5% while maintaining a 97.4% benign executable pass rate without human confirmation. TokenWall further introduces only 0.69 seconds of additional latency on benign cases, demonstrating that semantic runtime containment can achieve a practical security-utility trade-off for persistent AI agents.

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse generating unsafe content. We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position, significantly enhancing their safety capabilities. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation (MLE) with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence. Our empirical evaluation, conducted using LLaMA3 and Mistral model families across six attack scenarios, demonstrates that our method not only improves model safety without compromising performance but also surpasses well-known models such as GPT-4 in defending against attacks. Importantly, our approach successfully defends recent advanced attack methods (e.g., CodeAttack) that have jailbroken GPT-4 and LLaMA3-70B-Instruct. Our code and data can be found at https://github.com/RobustNLP/DeRTa.

Large Language Models (LLMs) are vulnerable to jailbreaksx2013methods to elicit harmful or generally impermissible outputs. Safety measures are developed and assessed on their effectiveness at defending against jailbreak attacks, indicating a belief that safety is equivalent to robustness. We assert that current defense mechanisms, such as output filters and alignment fine-tuning, are, and will remain, fundamentally insufficient for ensuring model safety. These defenses fail to address risks arising from dual-intent queries and the ability to composite innocuous outputs to achieve harmful goals. To address this critical gap, we introduce an information-theoretic threat model called inferential adversaries who exploit impermissible information leakage from model outputs to achieve malicious goals. We distinguish these from commonly studied security adversaries who only seek to force victim models to generate specific impermissible outputs. We demonstrate the feasibility of automating inferential adversaries through question decomposition and response aggregation. To provide safety guarantees, we define an information censorship criterion for censorship mechanisms, bounding the leakage of impermissible information. We propose a defense mechanism which ensures this bound and reveal an intrinsic safety-utility trade-off. Our work provides the first theoretically grounded understanding of the requirements for releasing safe LLMs and the utility costs involved.

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural language responses, their efficacy remains largely unexplored within multi-step tool-use trajectories. To address this gap, we introduce TraceSafe-Bench, the first comprehensive benchmark specifically designed to assess mid-trajectory safety. It encompasses 12 risk categories, ranging from security threats (e.g., prompt injection, privacy leaks) to operational failures (e.g., hallucinations, interface inconsistencies), featuring over 1,000 unique execution instances. Our evaluation of 13 LLM-as-a-guard models and 7 specialized guardrails yields three critical findings: 1) Structural Bottleneck: Guardrail efficacy is driven more by structural data competence (e.g., JSON parsing) than semantic safety alignment. Performance correlates strongly with structured-to-text benchmarks (ρ=0.79) but shows near-zero correlation with standard jailbreak robustness. 2) Architecture over Scale: Model architecture influences risk detection performance more significantly than model size, with general-purpose LLMs consistently outperforming specialized safety guardrails in trajectory analysis. 3) Temporal Stability: Accuracy remains resilient across extended trajectories. Increased execution steps allow models to pivot from static tool definitions to dynamic execution behaviors, actually improving risk detection performance in later stages. Our findings suggest that securing agentic workflows requires jointly optimizing for structural reasoning and safety alignment to effectively mitigate mid-trajectory risks.

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash against the very values alignment seeks to protect. In this paper, we propose the first method to auto-generate diverse, content-controlled, and model-dependent pseudo-harmful prompts. Using this method, we construct an evaluation dataset called PHTest, which is ten times larger than existing datasets, covers more false refusal patterns, and separately labels controversial prompts. We evaluate 20 LLMs on PHTest, uncovering new insights due to its scale and labeling. Our findings reveal a trade-off between minimizing false refusals and improving safety against jailbreak attacks. Moreover, we show that many jailbreak defenses significantly increase the false refusal rates, thereby undermining usability. Our method and dataset can help developers evaluate and fine-tune safer and more usable LLMs. Our code and dataset are available at https://github.com/umd-huang-lab/FalseRefusal

Recent advancements in large language model (LLM) agents have significantly accelerated scientific discovery automation, yet concurrently raised critical ethical and safety concerns. To systematically address these challenges, we introduce SafeScientist, an innovative AI scientist framework explicitly designed to enhance safety and ethical responsibility in AI-driven scientific exploration. SafeScientist proactively refuses ethically inappropriate or high-risk tasks and rigorously emphasizes safety throughout the research process. To achieve comprehensive safety oversight, we integrate multiple defensive mechanisms, including prompt monitoring, agent-collaboration monitoring, tool-use monitoring, and an ethical reviewer component. Complementing SafeScientist, we propose SciSafetyBench, a novel benchmark specifically designed to evaluate AI safety in scientific contexts, comprising 240 high-risk scientific tasks across 6 domains, alongside 30 specially designed scientific tools and 120 tool-related risk tasks. Extensive experiments demonstrate that SafeScientist significantly improves safety performance by 35\% compared to traditional AI scientist frameworks, without compromising scientific output quality. Additionally, we rigorously validate the robustness of our safety pipeline against diverse adversarial attack methods, further confirming the effectiveness of our integrated approach. The code and data will be available at https://github.com/ulab-uiuc/SafeScientist. red{Warning: this paper contains example data that may be offensive or harmful.}

For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically enforced in chat contexts, generalize to non-chat and agentic use cases? Unlike chatbots, LLM agents equipped with general-purpose tools, such as web browsers and mobile devices, can directly influence the real world, making it even more crucial to refuse harmful instructions. In this work, we primarily focus on red-teaming browser agents, LLMs that manipulate information via web browsers. To this end, we introduce Browser Agent Red teaming Toolkit (BrowserART), a comprehensive test suite designed specifically for red-teaming browser agents. BrowserART is consist of 100 diverse browser-related harmful behaviors (including original behaviors and ones sourced from HarmBench [Mazeika et al., 2024] and AirBench 2024 [Zeng et al., 2024b]) across both synthetic and real websites. Our empirical study on state-of-the-art browser agents reveals that, while the backbone LLM refuses harmful instructions as a chatbot, the corresponding agent does not. Moreover, attack methods designed to jailbreak refusal-trained LLMs in the chat settings transfer effectively to browser agents. With human rewrites, GPT-4o and o1-preview-based browser agents attempted 98 and 63 harmful behaviors (out of 100), respectively. We publicly release BrowserART and call on LLM developers, policymakers, and agent developers to collaborate on improving agent safety

Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic understanding to an isolated safety feature. In this work, we discover that safety-aligned behavior is jointly controlled by multi-dimensional directions. Namely, we study the vector space of representation shifts during safety fine-tuning on Llama 3 8B for refusing jailbreaks. By studying orthogonal directions in the space, we first find that a dominant direction governs the model's refusal behavior, while multiple smaller directions represent distinct and interpretable features like hypothetical narrative and role-playing. We then measure how different directions promote or suppress the dominant direction, showing the important role of secondary directions in shaping the model's refusal representation. Finally, we demonstrate that removing certain trigger tokens in harmful queries can mitigate these directions to bypass the learned safety capability, providing new insights on understanding safety alignment vulnerability from a multi-dimensional perspective. Code and artifacts are available at https://github.com/BMPixel/safety-residual-space.

Large Language Models used in ChatGPT have traditionally been trained to learn a refusal boundary: depending on the user's intent, the model is taught to either fully comply or outright refuse. While this is a strong mitigation for explicitly malicious prompts, focusing safety training on refusals can lead to brittleness for prompts with obscured user intent. Binary refusal boundaries are especially ill-suited for dual-use cases (such as biology or cybersecurity), where a user request can be answered safely at a high level, but in some cases can lead to malicious uplift if sufficiently detailed or actionable. As an alternative, we propose safe-completions: a safety-training approach that centers on the safety of the assistant's output, rather than a binary classification of the user's intent. Safe-completions seek to maximize helpfulness within the safety policy's constraints. We incorporated this approach into GPT-5 and find that across both production comparisons and internally controlled experiments, safe-completion training improves safety (especially on dual-use prompts), reduces the severity of residual safety failures, and substantially increases model helpfulness.

Large Language Models (LLMs) have recently gained attention due to their ability to understand and generate sophisticated human-like content. However, ensuring their safety is paramount as they might provide harmful and unsafe responses. Existing LLM testing frameworks address various safety-related concerns (e.g., drugs, terrorism, animal abuse) but often face challenges due to unbalanced and obsolete datasets. In this paper, we present ASTRAL, a tool that automates the generation and execution of test cases (i.e., prompts) for testing the safety of LLMs. First, we introduce a novel black-box coverage criterion to generate balanced and diverse unsafe test inputs across a diverse set of safety categories as well as linguistic writing characteristics (i.e., different style and persuasive writing techniques). Second, we propose an LLM-based approach that leverages Retrieval Augmented Generation (RAG), few-shot prompting strategies and web browsing to generate up-to-date test inputs. Lastly, similar to current LLM test automation techniques, we leverage LLMs as test oracles to distinguish between safe and unsafe test outputs, allowing a fully automated testing approach. We conduct an extensive evaluation on well-known LLMs, revealing the following key findings: i) GPT3.5 outperforms other LLMs when acting as the test oracle, accurately detecting unsafe responses, and even surpassing more recent LLMs (e.g., GPT-4), as well as LLMs that are specifically tailored to detect unsafe LLM outputs (e.g., LlamaGuard); ii) the results confirm that our approach can uncover nearly twice as many unsafe LLM behaviors with the same number of test inputs compared to currently used static datasets; and iii) our black-box coverage criterion combined with web browsing can effectively guide the LLM on generating up-to-date unsafe test inputs, significantly increasing the number of unsafe LLM behaviors.

Self-driving laboratories increasingly rely on low-cost liquid handlers such as the Opentrons OT-2, which ship without the pressure-based aspiration monitoring of Hamilton or Tecan systems and are typically run open-loop. Two failure modes go undetected: protocols that are syntactically valid but violate assay-specific invariants (e.g., tip reuse between a PCR template and a no-template control), and physical execution failures (partial dispense, air bubbles, missing tips) at runtime. We present AEGIS, a two-layer guardian for both. Layer 1 pairs a curated machine-readable assay rule database with an LLM that reasons over OT-2 Python code, reaching an adjusted F1 of 0.97 on a 24-protocol benchmark across five assay families and beating rules-only and LLM-only ablations across five backends; a free open-weight model ties the best proprietary one, so no paid API is required. Layer 2 fits a PCA world model to YOLO-cropped four-frame pipette trajectories; under a leakage-free leave-one-plate-out evaluation it reaches average precision 0.89 and operating-point F1 0.71 (AUROC 0.80), a deployment-faithful number that matches the live demonstration, and we characterize the small-pipette (p20) resolution limit (F1 0.47). A live demonstration on a physical OT-2 (five replicates per condition) catches planted no-tip failures deterministically and partial dispense on coloured dyes, with an always-VLM self-vote gate lifting partial-dispense recall to 5/5; transparent water is a principled limit of any front-view-only monitor, which AEGIS surfaces as low-confidence VLM reasoning rather than a wrong verdict. Cascade triage holds VLM cost near 1.63 per plate versus 10.33 for an always-VLM baseline. AEGIS is open source and, to our knowledge, the first system to unify pre-flight assay-aware validation with runtime visual monitoring for an open-source liquid handler.

LLM-agent budget overruns are a documented production failure class: a single retry loop can spend thousands of dollars before an operator notices, and the in-process integrity properties that would prevent it (no aliasing, no double-spend, no use-after-delegation of a cost-bearing value) are enforced, if at all, by ad-hoc wrappers rather than by the type system. Our central contribution is empirical: a catalog of 63 confirmed production incidents from 21 orchestration frameworks (2023-2026), each backed by a quoted GitHub issue and, where reported, a dollar loss, organized into an eight-cluster failure taxonomy (inter-rater Cohen's kappa = 0.837, N = 113), plus 47 supplementary structural entries. As one mitigation evaluated against this taxonomy, we build token-budgets, an 1,180-line Rust crate (no unsafe) that operationalizes affine ownership so that cloning, double-spending, or using a budget after delegating it are compile errors rather than runtime hazards an operator must remember to avoid. The dollar cap is runtime arithmetic under an estimator assumption; the affine layer makes that arithmetic non-bypassable. On single-agent workloads a 4-line Python counter matches the crate at 0/30 overshoot, so the distinguishing value is non-bypassability under operator error in multi-agent delegation: the delegation-fanout race documented in 11 incidents is rejected by the borrow checker at compile time, while the same pattern under asyncio overshoots 30/30 and three disciplined alternatives overshoot 0/30. Across five runtimes, three providers, and a temperature-stratified live-API test (N = 160), the approach reports zero cap violations and zero false refusals, at operational parity with concurrent work. Static over-reservation is 4-6x (2.11x adaptive). Binary-level cap-soundness on the running binary is left open.

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we propose SafeLLM, a novel unlearning-based defense framework that unlearn the harmful knowledge from LLMs while preserving linguistic fluency and general capabilities. SafeLLM employs a three-stage pipeline: (1) dynamic unsafe output detection using a hybrid approach that integrates external classifiers with model-internal evaluations; (2) token-level harmful content tracing through feedforward network (FFN) activations to localize harmful knowledge; and (3) constrained optimization to suppress unsafe behavior without degrading overall model quality. SafeLLM achieves targeted and irreversible forgetting by identifying and neutralizing FFN substructures responsible for harmful generation pathways. Extensive experiments on prominent LLMs (Vicuna, LLaMA, and GPT-J) across multiple jailbreak benchmarks show that SafeLLM substantially reduces attack success rates while maintaining high general-purpose performance. Compared to standard defense methods such as supervised fine-tuning and direct preference optimization, SafeLLM offers stronger safety guarantees, more precise control over harmful behavior, and greater robustness to unseen attacks. Moreover, SafeLLM maintains the general performance after the harmful knowledge unlearned. These results highlight unlearning as a promising direction for scalable and effective LLM safety.

Despite extensive safety alignment efforts, large language models (LLMs) remain vulnerable to jailbreak attacks that elicit harmful behavior. While existing studies predominantly focus on attack methods that require technical expertise, two critical questions remain underexplored: (1) Are jailbroken responses truly useful in enabling average users to carry out harmful actions? (2) Do safety vulnerabilities exist in more common, simple human-LLM interactions? In this paper, we demonstrate that LLM responses most effectively facilitate harmful actions when they are both actionable and informative--two attributes easily elicited in multi-step, multilingual interactions. Using this insight, we propose HarmScore, a jailbreak metric that measures how effectively an LLM response enables harmful actions, and Speak Easy, a simple multi-step, multilingual attack framework. Notably, by incorporating Speak Easy into direct request and jailbreak baselines, we see an average absolute increase of 0.319 in Attack Success Rate and 0.426 in HarmScore in both open-source and proprietary LLMs across four safety benchmarks. Our work reveals a critical yet often overlooked vulnerability: Malicious users can easily exploit common interaction patterns for harmful intentions.

Laboratory accidents pose significant risks to human life and property, underscoring the importance of robust safety protocols. Despite advancements in safety training, laboratory personnel may still unknowingly engage in unsafe practices. With the increasing reliance on large language models (LLMs) for guidance in various fields, including laboratory settings, there is a growing concern about their reliability in critical safety-related decision-making. Unlike trained human researchers, LLMs lack formal lab safety education, raising questions about their ability to provide safe and accurate guidance. Existing research on LLM trustworthiness primarily focuses on issues such as ethical compliance, truthfulness, and fairness but fails to fully cover safety-critical real-world applications, like lab safety. To address this gap, we propose the Laboratory Safety Benchmark (LabSafety Bench), a comprehensive evaluation framework based on a new taxonomy aligned with Occupational Safety and Health Administration (OSHA) protocols. This benchmark includes 765 multiple-choice questions verified by human experts, assessing LLMs and vision language models (VLMs) performance in lab safety contexts. Our evaluations demonstrate that while GPT-4o outperforms human participants, it is still prone to critical errors, highlighting the risks of relying on LLMs in safety-critical environments. Our findings emphasize the need for specialized benchmarks to accurately assess the trustworthiness of LLMs in real-world safety applications.

Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack surface. Existing studies have revealed unsafe agent behaviors induced by skill-based attacks, but they primarily evaluate poisoned skills within a single task execution and enumerate harms through ad-hoc risk lists. To bridge these gaps, we introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle, paired with a systematic taxonomy of skill-relevant risks. SkillHarm evaluates two attack scenarios: Fixed-Payload Poisoning (FPP), where a fixed poisoned skill package directly compromises any task session that invokes it, and Self-Mutating Poisoning (SMP), where an initially benign execution silently mutates persistent skill content, deferring harm until a subsequent reuse. It further defines 12 risk types based on the agent workflow component targeted by the harm: data pipelines, system environments, and agent autonomy. To instantiate these attacks at scale, we build AutoSkillHarm, an automated construction pipeline with coding agents driven by natural-language harnesses. The resulting benchmark contains 879 attack samples across 71 skills. Experiments show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP. Our analysis further reveals a latent risk: many apparent attack failures stem from the agent failing to engage with the poisoned file rather than genuine resistance, and current defenses still fail to reliably mitigate the threat.

Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems", where their ability to "interact in multi-turn, tool-augmented environments" makes them indispensable. However, ensuring the safety of these agents remains a significant challenge due to the diverse and complex risks arising from dynamic user interactions, external tool usage, and the potential for unintended harmful behaviors. To address this critical issue, we propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation. Concretely, 1) we introduce an open and extensible threat model, OTS, which formalizes how unsafe behaviors emerge from the interplay of user instructions, interaction contexts, and agent actions. This enables precise modeling of safety risks across diverse scenarios. 2) we develop a fully automated data generation pipeline that simulates unsafe user behaviors, applies self-reflective reasoning to generate safe responses, and constructs a large-scale, diverse, and high-quality safety training dataset-eliminating the need for hazardous real-world data collection. To evaluate the effectiveness of our framework, we design comprehensive experiments on both synthetic and real-world safety benchmarks. Results demonstrate that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks, validating the generalization ability of our learned safety strategies. These results highlight the practical advancement and scalability of AutoSafe in building safer LLM-based agents for real-world deployment. We have released the project page at https://auto-safe.github.io/.

Autonomous coding agents built on large language models (LLMs) are rapidly being integrated into development workflows, yet their operational safety properties remain poorly understood beyond evaluations of explicitly malicious inputs. In practice, high-impact failures arise during benign, goal-directed use through environment breakage, fabricated success reports, etc. that current benchmarks do not capture. What categories of operational safety failures actually occur when coding agents are used for everyday development tasks and what is their impact? We present an incident-driven empirical study grounded in two complementary evidence streams. We screen 68,816 papers from 22 premier venues, curating 185 safety-relevant studies, and mine 16,586 GitHub issues from widely deployed LLM-powered coding tools, manually confirming 547 genuine safety failures. Applying systematic open coding over both corpora, we derive a multi-dimensional safety taxonomy of 33 operational risk types organized across seven dimensions, and annotate each incident with contributing factors, task context, severity, and downstream impact. Our findings show that coding-agent failures are often severe, with 326 of 547 incidents rated high or critical. The dominant risks are constraint violations, destructive operations, authorization bypasses, and deception, and over 65% of incidents arise in bug fixing and setup or configuration, patterns largely missing from prior literature. These results have direct implications for SE tool designers and benchmark developers: guardrails must go beyond adversarial-prompt defenses to enforce environmental constraints, failure transparency, and safe-halt behaviors.

Recent advancements in large language models (LLMs) have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies primarily focus on reactively addressing jailbreak incidents after safety guardrails have been compromised, removing harmful gradients during fine-tuning, or continuously reinforcing safety alignment throughout fine-tuning. As such, they tend to overlook a critical upstream factor: the role of the original safety-alignment data. This paper therefore investigates the degradation of safety guardrails through the lens of representation similarity between upstream alignment datasets and downstream fine-tuning tasks. Our experiments demonstrate that high similarity between these datasets significantly weakens safety guardrails, making models more susceptible to jailbreaks. Conversely, low similarity between these two types of datasets yields substantially more robust models and thus reduces harmfulness score by up to 10.33%. By highlighting the importance of upstream dataset design in the building of durable safety guardrails and reducing real-world vulnerability to jailbreak attacks, these findings offer actionable insights for fine-tuning service providers.

LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a guard model that labels each proposed action as safe or unsafe, but this binary view conflates two distinct decisions: whether the action is harmful in itself, and whether it is appropriate given the user's context. It also operates at the granularity of action categories rather than individual instances, producing routine interruptions that erode autonomy and train users to wave through the most consequential alerts. We reframe the problem as a per-instance three-way routing decision over {EXECUTE, ASK, REFUSE} and instantiate it with Safety Sentry, a lightweight guard model whose inference reduces to a single decoding call. A single decoding-time threshold lets one fixed checkpoint be re-positioned across deployments of differing risk tolerance without retraining. Safety Sentry outperforms a broad set of open-weight and frontier closed-source baselines on overall accuracy and safety-related recall, while controlling both directional error rates simultaneously.

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict brittleness: among models above 90% baseline accuracy, brittleness rates range from 13.7% to 90.0%. Second, failures stem from policy override rather than miscomprehension: despite acknowledging the context change in every case, models persist via three distinct mechanisms that vary by update type and model family. Third, on a hand-audited probe of catastrophic consequence-flip scenarios, standard action-level guardrails catch none, while a state-aware validator catches all without false alarms on correct interventions. This indicates that action-level content moderation is systematically blind to consequence-flips, motivating state-aware architectural alternatives. We release our protocol, perturbed benchmarks, and deployment probe.

We introduce MacroBench, a code-first benchmark that evaluates whether LLMs can synthesize reusable browser-automation programs (macros) from natural-language goals by reading HTML/DOM and emitting Selenium. MacroBench instantiates seven self-hosted sites covering 681 tasks across interaction complexity and targeting difficulty. Our end-to-end protocol validates generated code via static checks, sandboxed execution, and outcome verification (DOM assertions, database snapshots), and includes a safety suite for scraping, spam/abuse, and credential/privacy prompts. Across 2,636 model-task runs, we observe stratified success: GPT-4o-mini (96.8%), GPT-4o (95.3%), Gemini (89.0%), DeepSeek (83.4%). Models handle simple tasks reliably (91.7%) but fail on complex workflows (0.0%), and none meet production-quality coding practices despite functional completion. We release our complete benchmark pipeline, evaluation framework, and experimental results at https://github.com/hyunjun1121/MacroBench to enable reproducible assessment of macro synthesis for web automation.

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world deployment. To tackle these emerging threats, we propose a lightweight and scalable agent safety alignment framework. Specifically, we update the agent safety taxonomy to accommodate emergent risks from Codex and OpenClaw execution scenarios. We further build a taxonomy-guided data engine with influence-function purification to train lightweight AgentDoG 1.5 variants (0.8B, 2B, 4B, and 8B parameters) using only around 1k samples, achieving comparable performance with leading closed-source models (e.g., GPT-5.4). Based on AgentDoG 1.5, we construct a highly efficient agentic safety SFT and RL training environment, which reduces deployment overhead in Docker-level environments by two orders of magnitude. Finally, we deploy AgentDoG 1.5 as a training-free online guardrail for real-time safety moderation. Extensive experimental results indicate that AgentDoG 1.5 achieves state-of-the-art performance in diverse and complex interactive agentic scenarios. All models and datasets are openly released.

Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an oversimplification that conflates two functionally distinct neural processes: the detection of harm and the execution of a refusal. In this work, we deconstruct this single representation into a Harm Detection Direction and a Refusal Execution Direction. Leveraging this fine-grained model, we introduce Differentiated Bi-Directional Intervention (DBDI), a new white-box framework that precisely neutralizes the safety alignment at critical layer. DBDI applies adaptive projection nullification to the refusal execution direction while suppressing the harm detection direction via direct steering. Extensive experiments demonstrate that DBDI outperforms prominent jailbreaking methods, achieving up to a 97.88\% attack success rate on models such as Llama-2. By providing a more granular and mechanistic framework, our work offers a new direction for the in-depth understanding of LLM safety alignment.

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values has become a paramount concern. Current safety benchmarks primarily evaluate whether agents refuse explicitly harmful instructions or whether they can maintain procedural compliance in complex tasks. However, there is a lack of benchmarks designed to capture emergent forms of outcome-driven constraint violations, which arise when agents pursue goal optimization under strong performance incentives while deprioritizing ethical, legal, or safety constraints over multiple steps in realistic production settings. To address this gap, we introduce a new benchmark comprising 40 distinct scenarios. Each scenario presents a task that requires multi-step actions, and the agent's performance is tied to a specific Key Performance Indicator (KPI). Each scenario features Mandated (instruction-commanded) and Incentivized (KPI-pressure-driven) variations to distinguish between obedience and emergent misalignment. Across 12 state-of-the-art large language models, we observe outcome-driven constraint violations ranging from 1.3% to 71.4%, with 9 of the 12 evaluated models exhibiting misalignment rates between 30% and 50%. Strikingly, we find that superior reasoning capability does not inherently ensure safety; for instance, Gemini-3-Pro-Preview, one of the most capable models evaluated, exhibits the highest violation rate at 71.4%, frequently escalating to severe misconduct to satisfy KPIs. Furthermore, we observe significant "deliberative misalignment", where the models that power the agents recognize their actions as unethical during separate evaluation. These results emphasize the critical need for more realistic agentic-safety training before deployment to mitigate their risks in the real world.

Agentic systems built on large language models (LLMs) extend beyond text generation to autonomously retrieve information and invoke tools. This runtime execution model shifts the attack surface from build-time artifacts to inference-time dependencies, exposing agents to manipulation through untrusted data and probabilistic capability resolution. While prior work has focused on model-level vulnerabilities, security risks emerging from cyclic and interdependent runtime behavior remain fragmented. We systematize these risks within a unified runtime framework, categorizing threats into data supply chain attacks (transient context injection and persistent memory poisoning) and tool supply chain attacks (discovery, implementation, and invocation). We further identify the Viral Agent Loop, in which agents act as vectors for self-propagating generative worms without exploiting code-level flaws. Finally, we advocate a Zero-Trust Runtime Architecture that treats context as untrusted control flow and constrains tool execution through cryptographic provenance rather than semantic inference.

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider's ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model's final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning.

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant/leading LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses to user queries. Our insight in developing SafeDecoding is based on the observation that, even though probabilities of tokens representing harmful contents outweigh those representing harmless responses, safety disclaimers still appear among the top tokens after sorting tokens by probability in descending order. This allows us to mitigate jailbreak attacks by identifying safety disclaimers and amplifying their token probabilities, while simultaneously attenuating the probabilities of token sequences that are aligned with the objectives of jailbreak attacks. We perform extensive experiments on five LLMs using six state-of-the-art jailbreak attacks and four benchmark datasets. Our results show that SafeDecoding significantly reduces the attack success rate and harmfulness of jailbreak attacks without compromising the helpfulness of responses to benign user queries. SafeDecoding outperforms six defense methods.

Model Context Protocol (MCP) servers enable AI applications to connect to external systems in a plug-and-play manner, but their rapid proliferation also introduces severe security risks. Unlike mature software ecosystems with rigorous vetting, MCP servers still lack standardized review mechanisms, giving adversaries opportunities to distribute malicious implementations. Despite this pressing risk, the security implications of MCP servers remain underexplored. To address this gap, we present the first systematic study that treats MCP servers as active threat actors and decomposes them into core components to examine how adversarial developers can implant malicious intent. Specifically, we investigate three research questions: (i) what types of attacks malicious MCP servers can launch, (ii) how vulnerable MCP hosts and Large Language Models (LLMs) are to these attacks, and (iii) how feasible it is to carry out MCP server attacks in practice. Our study proposes a component-based taxonomy comprising twelve attack categories. For each category, we develop Proof-of-Concept (PoC) servers and demonstrate their effectiveness across diverse real-world host-LLM settings. We further show that attackers can generate large numbers of malicious servers at virtually no cost. We then test state-of-the-art scanners on the generated servers and found that existing detection approaches are insufficient. These findings highlight that malicious MCP servers are easy to implement, difficult to detect with current tools, and capable of causing concrete damage to AI agent systems. Addressing this threat requires coordinated efforts among protocol designers, host developers, LLM providers, and end users to build a more secure and resilient MCP ecosystem.