code-review
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs its code review functions using standard command-line utilities like git and gh.
- [SAFE]: No malicious patterns, such as credential harvesting, persistence, or remote code execution from untrusted sources, were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from pull requests, creating a potential surface for indirect prompt injection, though the multi-step verification process serves as a mitigation. 1. Ingestion points: The skill reads PR titles, descriptions, and diff hunks using gh pr view and gh pr diff in SKILL.md. 2. Boundary markers: Absent; the instructions do not specify the use of delimiters for external content. 3. Capability inventory: The skill can read local files and PR data, and it has the ability to post comments to GitHub via gh pr comment as seen in SKILL.md. 4. Sanitization: No explicit sanitization or filtering of external input is described in the workflow.
Audit Metadata