code-review
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate instructions for performing professional code reviews. It promotes security best practices, such as verifying input validation and ensuring secrets are managed through environment variables rather than being hardcoded.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted data in the form of code diffs and PR descriptions. Given its primary purpose is code review, this surface is considered a routine risk associated with the use case.
- Ingestion points: The skill reads user-supplied code diffs, file lists, and branch descriptions as defined in the 'Inputs' section of SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the external content being reviewed.
- Capability inventory: The skill workflow involves discovery of project quality gates, which may lead to the execution of local linter or test commands. It also includes capability to write a tracking file (review.md) to the local file system.
- Sanitization: There is no mention of sanitizing or escaping the content of the code or descriptions before they are processed by the agent.
Audit Metadata