Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only brainstorming guide with no code, commands, persistence, credential access, or hidden execution behavior.
Install this if you want a Chinese-language structured brainstorming workflow. Be aware it may trigger on broad planning or decision-making requests; users who prefer another language or narrower activation should look for a version with clearer language and scope boundaries.
The skill description claims applicability to 'any scenario needing thought' across essentially all domains, which is overly broad for a skill-routing trigger. This can cause the agent to invoke the skill on vague or generic user requests, potentially hijacking normal conversations and steering users into this workflow when a more specific or safer skill should be used.
The skill is entirely written as Chinese-only guidance and does not indicate that the user may choose another language or that the locale restriction is intentional and justified. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
The usage section includes an unconstrained catch-all scenario ('任何需要"想清楚再动手"的事'), which broadens activation beyond well-defined tasks. In a multi-skill environment, this increases accidental invocation and can overshadow more appropriate domain-specific skills, reducing predictability and potentially bypassing intended guardrails.
