Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only Chinese decision-framing skill with no code execution, persistence, credential access, or hidden data flows.
Install this only if you want a Chinese-language framework for weighing decisions by cost, benefit, and evidence quality. For medical, legal, financial, emergency, or insurance matters, use it as a checklist for questions and tradeoffs, not as a substitute for current sources or a qualified professional.
The skill metadata and user-facing content are written to enforce Chinese-language behavior without indicating adaptation to the user's language preference. While not directly causing code execution or data exfiltration, this can create consent and usability problems, leading users to misunderstand safety caveats or high-stakes guidance if they are not fluent in Chinese.
The invocation scope is very broad and covers generic life-decision, legal-risk, health, insurance, and purchasing questions without strong boundaries. This can cause the skill to trigger on many common user queries and override more appropriate domain-specific handling, increasing the risk of unsafe or overconfident advice in regulated or high-stakes contexts.
This markdown file presents all instructions and templates exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or alternative language path is provided. The rule explicitly covers forced language constraints in natural-language content across all file types.
No suspicious patterns detected.
