canting-bikeng-zhinan
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable scripts (Python, Node.js, or Shell). All functionality is derived from text-based information retrieval and instructional guidance.
- [SAFE]: No network operations, API calls, or remote data fetching were detected. The skill operates entirely within the provided local markdown context.
- [SAFE]: No prompt injection or behavior override patterns were found. The instructions in SKILL.md provide standard persona guidance ("use a 'living' tone") and topical focus for the AI agent.
- [SAFE]: No sensitive data exposure or exfiltration risks identified. The content is public-facing renovation advice from the 'Xi'an Renovation Classroom' knowledge base.
- [SAFE]: Repetitive character sequences and number strings found in some reference files (e.g., ref-021.md, ref-028.md) appear to be non-malicious artifacts from the source content extraction or OCR, rather than obfuscated payloads.
Audit Metadata