code-review-web
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a set of instructional guidelines for code reviews. It correctly identifies and warns against common security risks like hardcoded secrets and unauthenticated mutation endpoints.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content such as code and logs, which is a standard surface for indirect prompt injection. This is inherent to the skill's purpose as an analysis tool.\n
- Ingestion points: User-provided code, PR descriptions, and server logs (SKILL.md).\n
- Boundary markers: None defined for the provided data.\n
- Capability inventory: Reading files and generating review reports.\n
- Sanitization: Not specified.
Audit Metadata