Security audit
Security checks for vulnerabilities and agentic risk
This is a small Chinese-language planning framework with disclosed triggers and no code, tool use, persistence, or sensitive data handling.
Install this if you want a Chinese-language framework that makes the assistant break tasks into goals, steps, risks, and execution order. Be aware that generic Chinese requests for structured planning may activate it, so use explicit /harnrss-style prompts when precision matters.
The entire skill is written to operate in Chinese and presents no option for the user to choose another language or locale. This can constitute a language-policy violation when the skill behavior is effectively constrained to a single language without explicit user opt-in or documented justification.
The trigger section uses broad natural-language phrases such as '用结构化能力' and '做个结构化规划', which are generic requests a user might make outside the intent of invoking this specific skill. This can cause accidental activation and instruction hijacking of normal conversations, making the assistant follow this skill when the user did not explicitly opt in.
No suspicious patterns detected.
