docs-claim-check

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

• Third-party content exposure detected (low risk: 0.10). The required workflow reads only user-supplied target text or user-designated files and evidence bundles, which the agent must select explicitly rather than receiving from an outsider-fed queue, so outsider-authored text (such as third-party docs or logs) reaches the model only through a specific user-chosen item.