hot-product-briefing
Warn
Audited by Snyk on Jun 29, 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). 该技能在“产品数据采集”阶段会调用外部金融数据 MCP(如 qieman 的
BatchGetFundsDetail/GetBatchFundPerformance/GetFundDiagnosis/AnalyzeFundRisk或 gildata-aidata 的ProductBasicInfoList/FundManagerInfoReport),这些工具返回的文本/字段会被用于“卖点提炼”,从而把非用户自写的第三方数据内容(外部数据服务的自由文本/描述)注入到LLM上下文中。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata