gr-user-interview
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md 的“Token Top10 访谈法”要求把用户录屏/转写 transcript 交给 AI(“Transcript 喂 AI”)并据此生成 feature/bug 文本;该 transcript 来自被访谈的外部用户(outsider-authored free text),会进入 LLM 上下文形成间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata