code-review-excellence
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code diffs and repository content which are subject to indirect prompt injection attacks where malicious instructions are hidden in comments or code to influence the reviewer's output.
- Ingestion points: Code diffs and repository files referenced in SKILL.md.
- Boundary markers: Instructions explicitly advise treating repository text as untrusted evidence.
- Capability inventory: The skill is limited to analysis and reporting; no tools for network or filesystem modification are requested.
- Sanitization: No automated sanitization of ingested content is defined.
Audit Metadata