Security audit
Security checks for vulnerabilities and agentic risk
This is a simple business-idea validation coaching skill with no code execution, data access, persistence, or hidden behavior.
Install this if you want Chinese-language guidance for validating business ideas before building. Be aware it may activate on broad idea-validation or startup phrasing, including the English phrase "validate idea," so users who prefer another language may need to ask the agent to translate or avoid invoking it.
The skill is authored entirely in Chinese and does not offer language negotiation, fallback behavior, or a documented locale restriction. If invoked for users operating in other languages, it can produce inaccessible or misunderstood guidance, increasing the chance of user confusion, incorrect decisions, or failure to follow important business-validation steps.
The trigger keywords and read_when conditions are broad enough to match many ordinary startup or product discussions, which can cause the skill to activate when the user did not explicitly request this validation framework. That creates context hijacking risk: the assistant may steer conversations into prescriptive business advice, suppress better-matched skills, or apply the wrong workflow to ambiguous requests.
No suspicious patterns detected.
