clean-code

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and refactor external source code, creating a surface for indirect prompt injection.\n
  • Ingestion points: SKILL.md instructs the agent to activate during code reviews and refactoring tasks.\n
  • Boundary markers: The skill does not provide delimiters or specific instructions to ignore embedded prompts within the code being analyzed.\n
  • Capability inventory: The skill assumes the agent can perform file read/write and potentially run tests on the codebase.\n
  • Sanitization: There is no instruction to sanitize or validate the content of the files before processing.\n- [COMMAND_EXECUTION]: The skill includes a Python script (eval/run_eval.py) for validating documentation integrity.\n
  • The script uses the Python standard library to perform local file reads and temporary directory management.\n
  • These actions are confined to the skill's own directory and a system-defined temporary path for validation purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:07 PM
Security Audit — agent-trust-hub — clean-code