pr-review-static
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide structured guidance for code reviews. It includes proactive security checks, such as identifying hardcoded tokens or secrets in documentation files (Checklist Item 20).
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze untrusted data (code diffs from a repository). However, the risk is negligible as the skill only performs read operations for context and does not have the capability to execute the code it reviews or perform network exfiltration.
- Ingestion points: Code diffs accessed via
git diff(SKILL.md). - Boundary markers: Absent.
- Capability inventory: Read-only command execution for Git diffs; no file-write or network capabilities detected.
- Sanitization: Absent.
Audit Metadata