hospital-skill
Warn
Audited by Snyk on Aug 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). 该技能在运行时会把用户/外部模型生成的结构化字段(例如 searchHospitals 的
keyword,以及 booking/getMyAppointments 返回的patientName/医院/科室/医生信息)通过wx.modelContext的NotificationType.Result写入structuredContent,并在组件卡片模板中直接展示;其中searchHospitals接口接收的keyword可由用户原话构造并触发返回文本/字段流入组件。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata