Security audit
Security checks for vulnerabilities and agentic risk
This is a content-structuring methodology skill with disclosed user-choice workflows and no executable code, persistence, credential use, or hidden behavior.
Installers should understand this skill may appear for many structured writing tasks and is primarily Chinese-language. It is reasonable to install if you want a generic content-composition workflow, but prefer more specialized skills for regulated, technical, legal, medical, or other high-stakes work.
The skill is designed to trigger for a very broad class of requests, including essentially any request for structured output when no method is specified. That can cause it to preempt more domain-specific or safer skills, leading the agent to apply generic content-generation workflows in contexts where specialized constraints, safety rules, or expertise are required.
The natural-language instructions and user-facing interaction template are entirely in Chinese, but the file does not state that the skill is China-specific or that users may choose another language. This can amount to a language/locale policy issue because it implicitly forces one language without opt-in.
No suspicious patterns detected.
