review-hog-resolution-criteria-small
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from pull request review comments, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Pull request review threads (comments) and repository code as described in SKILL.md.
- Boundary markers: None explicitly defined to isolate untrusted comment content.
- Capability inventory: Includes the ability to implement code changes and commit them to the repository (the 'fixed' outcome).
- Sanitization: The skill implements mitigation strategies such as 'Trust-weighted' assessment (weighting maintainers over unknown commenters) and 'Provable in-session' checks (requiring evidence from linting and tests before committing).
Audit Metadata