receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data in the form of code review comments from external reviewers.
- Ingestion points: External feedback received through the agent's context as described in
SKILL.md. - Boundary markers: The instructions explicitly implement internal boundary markers by requiring the agent to "VERIFY" suggestions against the codebase reality and "EVALUATE" them before implementation.
- Capability inventory: The skill allows for code implementation and utilizes the GitHub API via the
gh apicommand for thread replies. - Sanitization: The skill emphasizes skepticism and technical validation as a primary defense against incorrect or malicious external feedback.
Audit Metadata