Skills
skills/chearmstrong/skills/review-comments/Gen Agent Trust Hub

review-comments

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes code review comments from untrusted external sources (GitHub UI, Copilot, subagents), which constitutes an indirect prompt injection surface. The risk is mitigated by explicit instructions to treat inputs as hypotheses rather than instructions, requiring independent verification against the codebase and official documentation before implementation.
  • [COMMAND_EXECUTION]: The utility script scripts/validate_handoff.py uses subprocess.run to execute git diff commands. The execution is handled safely using argument lists (avoiding shell interpolation) and includes rigorous path validation to ensure file access does not escape the repository root.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 06:17 PM
Security Audit — agent-trust-hub — review-comments