Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese-language brainstorming helper that creates design plans and does not show hidden data access, network use, or destructive behavior.
Install this if you want a Chinese-language design-planning workflow. Before using it in a repository, make sure the agent asks before creating files under docs/plans or running git commit, especially if the planning document may contain private product or architecture details.
The manifest description forces a specific language/locale presentation ('把模糊想法变成可执行方案。唤醒词...') with no indication that users can choose another language. Under the policy, locale or language constraints should not be imposed without user opt-in unless clearly justified as region-specific.
The title and description specify output templates entirely in Chinese, presenting the skill's expected output language as fixed rather than optional. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.
The skill explicitly instructs the agent to write a design document into the repository and then commit it to git, but it does not require a clear user confirmation immediately before modifying files or creating commits. In an agentic environment, this can lead to unintended workspace changes, polluting repositories or persisting sensitive planning content without the user's informed approval.
The title and introductory description are written only in Chinese, which imposes a specific language on users. The file does not indicate that this is a region-specific skill or offer any language/locale opt-in, matching the policy's language/locale violation criterion.
文件标题和全文内容均以中文固定呈现，且未说明这是仅面向中文用户的区域性模板，也没有提供语言选择或用户自愿选择中文的机制。根据规则，若技能在自然语言层面强制特定语言而无用户选择，属于语言/locale 策略问题。
No suspicious patterns detected.
