xunzi-perspective
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown documentation, persona instructions, and research materials. It does not include any scripts (Python, Node.js), executables, or binary files that could perform actions on the host system.
- [SAFE]: All external links and repository references trace back to the author's own infrastructure ('nuwa-skills') or reputable sources (GitHub, academic citations). The installation instruction 'npx skills add nuwa-skills/xunzi-skill' is standard for the platform.
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with user queries to provide philosophical advice. While this processes external data, the skill is scoped to text generation and does not request tools or permissions for network access, file system modifications, or command execution, mitigating risks from potential injection attacks.
Audit Metadata