Security audit
Security checks for vulnerabilities and agentic risk
This is a simple decision-bias reference skill that does not run code, request sensitive access, or create persistence.
Install this if you want decision advice framed through Kahneman-style cognitive-bias concepts. Be aware that it is written in Chinese and may influence broad decision-help prompts, so use specialist advice for legal, medical, financial, or other high-stakes domains.
The description is written as a Chinese-only user-facing skill description, and the file provides no indication that users may choose another language or that the locale restriction is intentional and justified. Under the policy, language constraints should either be optional for the user or clearly documented as region-specific.
The activation text is broad enough to match many generic decision-help requests, which can cause the skill to trigger outside narrowly intended contexts. This is primarily a scope-control and prompt-routing issue: it may inject this book-based framework into unrelated conversations, reducing response relevance and potentially overriding more suitable specialized guidance.
No suspicious patterns detected.
