receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill is designed to process untrusted data in the form of external code review feedback.
- Ingestion points: External feedback from human reviewers and PR comments ingested at runtime.
- Boundary markers: Absent, however, the skill provides explicit instructions to verify feedback against the codebase reality before implementation.
- Capability inventory: The skill uses
grepfor local file searching andgh apifor interacting with GitHub pull request comments. - Sanitization: The skill mandates a technical evaluation phase ('VERIFY' and 'EVALUATE') which serves as a cognitive filter against malicious or incorrect suggestions embedded in feedback.
- [Command Execution] (SAFE): The skill employs standard development tools (
grep) and the GitHub CLI API for legitimate code review workflows. The API usage targets whitelisted GitHub domains and follows a rigid path structure.
Audit Metadata