audit-code
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on auditing local code changes and project documentation. It instructions the agent to read specific paths like projects/site/src/docs/internal/guidelines/ and use Git commands to retrieve staged files. These actions are within the expected scope of a code review tool.
- [SAFE]: The skill processes external data (staged code) which is a potential surface for indirect prompt injection. However, this is inherent to the code review process. Evidence chain: 1. Ingestion points: Git staged files and local markdown documentation. 2. Boundary markers: None. 3. Capability inventory: Local file read access. 4. Sanitization: None provided. Given its use-case, this is considered a safe application of the agent.
Audit Metadata