wangyangming-perspective
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions for the agent to adopt a specific persona ('王阳明') and follow role-playing rules, such as using first-person pronouns and staying in character. These are standard implementation details for a personality-driven skill and do not attempt to override the AI's core safety guidelines or bypass underlying constraints.
- [COMMAND_EXECUTION]: The README provides an installation command
npx skills add nuwa-skills/wangyangming-skill. This is a documented method for skill distribution on the platform and refers to the author's official repository. - [SAFE]: The skill's functionality is entirely focused on text-based philosophical modeling. It does not perform network operations, access sensitive files, include hardcoded credentials, or use dynamic code execution patterns. All external references are to the author's own documentation or established repositories related to the skill's stated purpose.
Audit Metadata