review
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill provides clear instructions for code analysis without requesting dangerous permissions or executing external code.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted content such as PR descriptions and code diffs.
- Ingestion points: PR descriptions, commit messages, and diff content as described in SKILL.md.
- Boundary markers: None specified to separate untrusted code data from the agent's instructions.
- Capability inventory: No dangerous capabilities (e.g., shell access, network requests) are defined or utilized within this skill.
- Sanitization: No explicit sanitization or instructions to ignore embedded commands in the input data are provided.
Audit Metadata