fto-report-quality
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skill的运行流程会在“独立检索验证与漏检核查”中调用 MCP 工具
patsnap_search执行五轨检索,并将检索返回的专利字段(如专利标题、申请人、法律状态、URL等)写入报告数据后由scripts/generate_report.py渲染为HTML,因此其外部(用户/他人提交的输入经由检索检索命中后)会让LLM在运行时摄入由外部作者产生的自由文本元数据;虽然不会主动抓取任意网页,但它会读取独立检索结果中的文本内容。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata