shaman-sun-tzu
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill files contain only instructional text and metadata designed to guide the AI's persona. No technical security vulnerabilities or malicious patterns were identified during the analysis of the prompts and structural frameworks.
- [NO_CODE]: The skill does not include any executable scripts, shell commands, or external dependencies. It relies entirely on natural language instructions for strategic reasoning.
- [PROMPT_INJECTION]: While the skill uses strong persona-enforcement language (e.g., 'digital soul of Sun Tzu'), these instructions are limited to character roleplay and do not attempt to bypass system safety guidelines or extract underlying system prompts.
Audit Metadata