Security audit
Security checks for vulnerabilities and agentic risk
This is a simple advisory skill for validating business ideas and does not request code execution, credentials, persistence, or access to private data.
Install this if you want a Chinese-language coaching framework for testing whether people will pay for a business idea before you build it. Be aware it may apply its framework broadly to idea-evaluation conversations and may answer in Chinese unless your agent adapts language to your preference.
The description, triggers, and operating instructions all assume Chinese output and interaction, while there is no statement that the skill is intended only for Chinese-speaking users or that language is selectable. This can violate language/locale policy by implicitly forcing a specific language without user opt-in.
The trigger and read_when conditions are broad enough that this skill could activate during general discussions about starting projects or evaluating ideas, not just when the user explicitly wants this framework. That can cause unintended routing or over-application of the skill, which is a prompt-scoping weakness, though it does not directly create code execution or data exfiltration risk.
No suspicious patterns detected.
