pharma-company-intelligence
Warn
Audited by Snyk on Aug 27, 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). 该技能在运行时会通过
web.search+web_fetch(Step 1/2/3/5)以及paper.search/patent.search读取互联网上的第三方文本与元数据(如官网 pipeline 页面、press release、临床与媒体内容、论文摘要、专利公开文本),从而可能被外部作者在这些可发布内容中注入恶意指令。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata