review-codebase
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats identified. The skill consists exclusively of markdown-based instructions for the AI to perform a code review task.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external codebase content, which is a surface for indirect prompt injection. However, this is part of its core functionality and no dangerous capabilities are present to be exploited. Ingestion points: File and directory paths (SKILL.md). Boundary markers: Absent. Capability inventory: None. Sanitization: Absent.
Audit Metadata