li-three-word-qa
Warn
Audited by Snyk on Jul 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md 第三步会“问学员/引导学员逐组提供”,把学员的自由文本(外部用户输入,非操作用户自写)用于方案A/B的生成与汇总,从而进入LLM上下文;同时第二步读取的 structure.md 是同目录自带材料(不计为外部)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata