office-research
Warn
Audited by Snyk on Jul 6, 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). 该技能的“方法”要求在“有 web 工具时先检索再归纳”,因此运行时会读取并总结公开网页/检索结果中的自由文本(OUTSIDER:公共 web 内容),将其作为可读 prose 进入代理的 LLM 上下文。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata