git-pr-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of Git diffs and code changes which can be used to influence the AI agent's behavior.
- Ingestion points: External data is ingested via
git diffoutput when reviewing pull requests. - Boundary markers: The instructions do not define clear delimiters or boundary markers to separate the skill's instructions from the code content being analyzed.
- Capability inventory: The skill is authorized to use
Bash,Read,Grep, andGlobtools to access and analyze the local environment. - Sanitization: There are no specified sanitization methods or explicit 'ignore embedded instructions' warnings for the data being processed.
Audit Metadata