code-review
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code from git diffs, local files, and external pull requests, which could contain instructions designed to deceive the agent during its review.
- Ingestion points: Where untrusted data enters the agent context via
git diff HEADand file reading operations. - Boundary markers: The instructions lack explicit markers or warnings to help the agent distinguish between its own system instructions and the content of the code being reviewed.
- Capability inventory: The skill has the ability to run shell commands (
git diff) and read files on the local system. - Sanitization: There is no mention of sanitizing or escaping the content of the changes before they are analyzed by the AI.
Audit Metadata