Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language Taleb-style reasoning skill made only of Markdown guidance, with no code execution, data access, persistence, or hidden install behavior.
Install this if you want Chinese-language Taleb-inspired analysis. Be aware that common terms like 黑天鹅 or 反脆弱 may trigger this perspective even when you did not explicitly ask for it, and the skill may answer in Chinese unless your agent handles language preference separately.
The trigger list includes broad conceptual phrases such as “黑天鹅” and “反脆弱”, which are common terms in general discussion and can cause the skill to activate outside the author’s intended context. Unintended invocation can steer unrelated conversations into this persona/framework, degrading system behavior and potentially overriding more appropriate skills.
The skill metadata and trigger design are written to operate in Chinese without any indication of respecting the user's current language preference. If auto-activated, this can override user expectations and cause unwanted language switching, which degrades reliability and may obscure important safety guidance or system behavior.
The trigger phrases include very common terms such as '黑天鹅', '反脆弱', and '杠铃策略', which can appear in ordinary discussion without an explicit request to invoke the skill. This can cause unintended activation and persona injection, leading the assistant to adopt the Taleb framing in contexts where the user did not clearly opt in.
This markdown file presents all user-facing natural-language content in Chinese, including the title and section labels, with no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.
This markdown file presents all user-facing content exclusively in Chinese, and there is no indication that the user can choose another language or that the Chinese-only scope is intentional. Under the natural-language policy rules, forcing a specific language without user opt-in can be a locale-policy violation.
The entire skill-facing content is written in Chinese, with no indication that language choice is optional or that the file is intended only for a Chinese-language or region-specific context. Under the policy rule, a fixed language requirement without user opt-in or explicit justification is a natural-language policy concern.
The skill content and description are entirely in Chinese and do not indicate any user language choice or fallback behavior. This can cause the skill to respond in an unexpected locale when invoked, creating usability and interpretation risks, especially if activation is triggered by ambiguous terms.
No suspicious patterns detected.
