feng-shui
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior detected. The skill uses standard file system analysis tools to evaluate project structure and file placement for its assessment.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads untrusted codebase content to perform its analysis.
- Ingestion points: Local repository files are scanned using Read, Grep, and Glob (SKILL.md, Step 4).
- Boundary markers: Not present.
- Capability inventory: The skill utilizes LS, Read, Grep, Glob, Execute, and AskUser.
- Sanitization: No sanitization is performed on the ingested code content before it is processed by the agent.
Audit Metadata