code-review-excellence
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of code changes and pull request descriptions. This represents a potential surface for indirect prompt injection, where malicious instructions could be embedded in the code being reviewed.
- Ingestion points: Pull request descriptions and code snippets provided for review.
- Boundary markers: The skill provides logical structure for the review process but does not define explicit delimiters to separate untrusted code from agent instructions.
- Capability inventory: The skill primarily provides guidance and templates; it references a local script
scripts/pr-analyzer.pyfor complexity analysis, but does not invoke network or file-writing capabilities in the provided instructions. - Sanitization: None specified for the input data.
Audit Metadata