fengshui-master
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill is composed of static Markdown reference files and instructions. It does not contain any executable scripts, binaries, or command-line operations that could pose a security risk to the host environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided data about living environments and personal birth information. This creates a standard interaction surface common to AI agents. The instructions include specific boundaries and a defined persona ('堪舆子') to ensure inputs are processed within the context of traditional Feng Shui advisory rather than executing unintended commands.
- [EXTERNAL_DOWNLOADS]: The documentation references installation through well-known tools like
npx skillsand official repositories from trusted organizations. These references are for installation purposes and do not involve the skill downloading or executing remote code at runtime.
Audit Metadata