Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese writing-coaching skill that asks reflective questions and produces writing-positioning advice, with no code execution, persistence, or hidden data access.
Install this if you want a Chinese-language guided writing retrospective. Expect it to ask about achievements, regrets, motivation, audience, and why writing stopped; avoid sharing private personal details you do not want used in the conversation.
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
给出 3 个以内、可以立刻执行的动作。
## Output Rules
- 不要只做分析，必须落到动作
- 不要给超出当前阶段的复杂体系设计
The skill description includes broad trigger phrases such as general writing-direction and writing-help requests, which can cause the agent to invoke this deep-review workflow for ordinary tasks like ideation or light editing. Over-broad routing is risky because it can override user intent, collect unnecessary personal reflective information, and degrade safety by pushing a psychologically probing flow outside its intended scope.
The description, workflow, and example opening are entirely in Chinese and implicitly require Chinese-language interaction, but the file does not state that this is optional or limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.