ai-churn-prevention
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). 该技能的运行时上下文由用户在
materialText/materialFile/materialUrl中提供的“页面文案/流程说明/实验想法/反馈/阻力线索”等自由文本或由链接/文件解析出的可读内容组成；其中若materialUrl指向外部网页或materialText/文件来自非操作用户，则会把 OUTSIDER 的自由文本读入 LLM（contextComposer）。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata