Security audit
Security checks for vulnerabilities and agentic risk
This skill is a repository documentation assistant that asks to inspect a user-specified project and generate docs, with no hidden execution, credential use, or persistence found.
Before installing, be aware that this skill is designed to read a substantial portion of a repository and create self-contained documentation. Use it on codebases you are comfortable documenting, choose an appropriate output directory, and review generated docs for sensitive implementation details before sharing them.
The trigger list includes broad, generic phrases such as '生成文档', '代码分析', and '项目总览' that can match many ordinary requests unrelated to this specific skill. This increases the chance of unintended activation, which can cause the agent to apply repository-wide analysis behavior in the wrong context, consume excessive context/tokens, and override more appropriate specialized skills.
Defaulting to Chinese when the user's language is unclear imposes a language choice without explicit consent. While not a classic security flaw, it can degrade usability, cause misunderstanding of analysis results, and create operational risk if users misinterpret documentation or prompts due to unexpected language selection.
The English section does not provide equivalent full instructions; instead, it tells users to read the Chinese section and translate it if needed. This effectively privileges one language and may disadvantage users who did not opt into Chinese-centric behavior.
No suspicious patterns detected.
