Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed strategic planning framework for deciding when and how to use agents, with no evidence of hidden execution, data theft, persistence, or destructive behavior.
Installers should expect this skill to influence agent-planning discussions with an Art of War-style framework and some Chinese terminology. Review whether that style and language mix fits your users; authorize any real-world tool, API, database, or monitoring access separately if an agent later proposes using it.
The activation triggers are broad enough to match ordinary conversations about planning, budgeting, or collaboration, which can cause the skill to engage outside its intended niche. In a prompt-driven agent environment, over-broad auto-activation can inappropriately steer responses, override more relevant skills, or inject domain framing into unrelated tasks.
This markdown skill includes substantial operational instructions in Chinese, including mandatory checklist language such as '必用' and '填不完别发', without indicating that the user can choose another language. That can violate a language/locale policy when the skill effectively requires a specific language for correct use.
The chapter mappings and surrounding guidance prominently use Chinese terms such as '始计篇' and '用间篇' as operational labels, but the README does not state that this language usage is optional or provide a user opt-in. This can conflict with language/locale policies when users expect guidance in their chosen language.
The file header and later user-facing text include Chinese phrases alongside English, but the script does not give the user any option to select or opt into a preferred language or locale. This can violate a language/locale policy when users are implicitly forced into a language presentation they may not understand.
No suspicious patterns detected.
