README.md

metadata

license: apache-2.0
tags:
  - layerfault
  - security-research
  - model-security
  - synthetic
  - adversarial-testing
extra_gated_prompt: >-
  This repository is a synthetic security-test artifact from the Layerfault
  corpus. It intentionally contains adversarial characteristics (e.g. suspicious
  pickle opcodes, executable-format smuggling, prompt-injection strings)
  designed to exercise security scanner detection rules. It is **not** a usable
  ML model and must never be loaded or executed outside an isolated
  scanner-testing environment. By accepting, you confirm you understand this
  repository is a test fixture, not production model weights.
extra_gated_button_content: I understand this is a security test fixture and accept the risk
gated: auto

python-custom-loader-capability-chain

SECURITY TEST ARTIFACT: DO NOT USE AS A PRODUCTION MODEL

This repository is part of the Layerfault synthetic security corpus. It is deliberately constructed to contain security-relevant characteristics for scanner testing.

Corpus ID: LF-CORPUS-PY-0001

Purpose

HF-style custom loader containing harmless process, native-load, loopback-network, credential, filesystem, dynamic-code, package-manager and NumPy allow_pickle call sites.

Direct expected Layerfault rules

• LF-CODE-AUTO-MAP
• LF-CODE-SUBPROCESS
• LF-PY-CALL-PROCESS
• LF-CORR-HF-LOADER-PROCESS
• LF-CODE-CTYPES
• LF-PY-NATIVE-LOAD
• LF-CORR-HF-LOADER-NATIVE-LOAD
• LF-CODE-NETWORK
• LF-PY-CALL-NETWORK
• LF-CORR-HF-LOADER-NETWORK
• LF-PY-CREDENTIAL-ACCESS
• LF-CORR-HF-LOADER-CREDENTIALS
• LF-PY-FILESYSTEM-MUTATION
• LF-CORR-HF-LOADER-FILESYSTEM
• LF-CODE-EVAL
• LF-PY-CALL-DYNAMIC-CODE
• LF-CORR-HF-LOADER-DYNAMIC-CODE
• LF-PY-PACKAGE-INSTALL
• LF-CORR-HF-LOADER-INSTALL
• LF-PY-NUMPY-ALLOW-PICKLE
• LF-CORR-NUMPY-ALLOW-PICKLE

Candidate rules

These are deliberately plausible targets that remain marked as candidates until the exact Layerfault build used for certification confirms them.

• None

Negative-control rules

These should remain silent for this corpus item.

• None

Safety

The corpus uses fake secrets, loopback/.invalid network destinations, harmless marker output, and synthetic model behavior only. It is intended for static scanning and isolated security testing.