code-review-expert
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from source code diffs and specification documents, and has the capability to modify files when applying minor bug fixes. Ingestion points: git diffs and external Spec files (SKILL.md). Boundary markers: The skill requires an 80% confidence threshold and direct evidence from code lines or Spec clauses (SKILL.md). Capability inventory: File reading and writing/modification (SKILL.md). Sanitization: No explicit sanitization or escaping is mentioned for input code content.
- [SAFE]: The skill's internal guidelines proactively mandate the identification of security risks, such as hardcoded credentials, input validation errors, and the leakage of sensitive data like tokens or passwords in logs (references/dimensions.md and references/severity-calibration.md).
Audit Metadata