respond-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from pull request feedback and code review comments, creating a surface for indirect prompt injection attacks.
- Ingestion points: Feedback is gathered from pull request threads, issue feedback, and code review comments using GitHub tools (SKILL.md).
- Boundary markers: There are no explicit delimiters or sanitization steps mentioned for the ingested feedback text to prevent it from being interpreted as instructions.
- Capability inventory: The agent can inspect repository context, edit files, run verification tests, and post comments to GitHub threads (SKILL.md).
- Sanitization: The skill lacks explicit sanitization, filtering, or escaping instructions for the external feedback content.
Audit Metadata