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
Risk Level
SAFE
Analyzed
Jul 3, 2026, 10:07 AM
Security Audit — agent-trust-hub — feng-shui