Security audit
Security checks for vulnerabilities and agentic risk
This is a simple medical-visit preparation checklist skill with no code, network access, persistence, or hidden data handling.
Before installing, users should understand that this skill is for organizing information before a medical visit, not for diagnosis. Because it may handle sensitive health details, share only what is necessary and avoid entering identifying information unless needed for the conversation.
The trigger keywords are broad, common-language phrases such as '看病前准备' and '怎么跟医生说' that could match ordinary user conversation and activate the skill unintentionally. In a medical-context skill, accidental activation can cause users to disclose sensitive health information to the wrong workflow or receive prep-oriented output when they did not intend to invoke this skill.
The natural-language examples are open-ended and underspecified, for example '帮我看病前把该带的、该说的、该问的准备好' and '把这些整理成一张表', which could overlap with many normal chat requests. This increases the chance of unintended routing and, in this healthcare context, may expose private medical details or produce advice-like outputs without a clearly scoped request.
No suspicious patterns detected.
