integration-management

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and parses external transaction documents (e.g., "上传或已连接的文件路径" in 模式1, "你的合同存储库是否已连接？…我将拉取…并逐份读取" in 模式2, and "上传来自[外部律师/…]的状态更新。我将解析并更新追踪器" in 模式4), meaning it consumes untrusted/third‑party user-generated content and uses that content to drive decisions and workflow actions.