code-review
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides defensive security instructions, asking the agent to check for secrets and input validation issues in reviewed code.
- [SAFE]: No prompt injection, obfuscation, or remote code execution patterns were identified.
- [SAFE]: Indirect Prompt Injection surface: The skill processes external pull request data (SKILL.md). Boundary markers and sanitization are absent, but the skill lacks access to exploitable capabilities or tools in its definition.
Audit Metadata