Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only brainstorming skill for innovation ideas, with no code execution or data access, though its broad triggers and Chinese-only presentation may cause unexpected activation or language mismatch.
Install this if you want a Chinese-language framework for structured innovation brainstorming. Be aware that common words about innovation or breakthroughs may route requests into this skill, and treat outputs for legal, investment, policy, medical, or other sensitive areas as brainstorming that needs independent expert review.
The trigger list is extremely broad and includes common terms like '创新', '突破', and '第一性原理', which are likely to appear in ordinary user conversations unrelated to this skill. This can cause accidental activation, unexpected context injection, and inappropriate steering of the assistant into the skill's behavior when the user did not explicitly request it.
The file presents all instructions, workflow, triggers, and output format in Chinese and does not state that users may choose another language. Per the policy, forcing a specific language without user opt-in is a natural-language policy concern unless a locale-specific justification is documented.
The trigger examples are broad enough that ordinary requests about ideas, breakthroughs, strategy, or improvement could activate this skill unintentionally. That can cause prompt hijacking at the orchestration layer, where a generic user request is routed into an expansive 'any domain' innovation workflow that may generate inappropriate or unsafe outputs for sensitive domains without clear user intent.
Natural-language content in the description and body consistently assumes Chinese as the operating language, but the file does not state that this is a region-specific skill or offer an opt-in language preference. That creates a language policy concern because users are not given a choice of locale or language.
