security-review
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are focused on guiding the agent to perform security audits of code diffs. It does not include any malicious commands, obfuscation, or unauthorized data access patterns.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (git diffs and pull request content), which presents a surface for indirect prompt injection. 1. Ingestion points: Data enters the context via git diff and gh pr diff commands as specified in SKILL.md. 2. Boundary markers: None are explicitly defined for the data ingestion process. 3. Capability inventory: The skill primarily reads data and performs analysis; it does not contain instructions for file writes or unauthorized network requests. 4. Sanitization: There are no explicit sanitization or filtering steps mentioned for the processed diff content. However, the instructions explicitly direct the agent to 'assume the diff is hostile until proven safe', which serves as a conceptual safeguard.
Audit Metadata