ai-crm-cleanup

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

• Third-party content exposure detected (high risk: 0.75). The skill’s required runtime workflow can ingest outsider-authored free text via user-supplied materialText (and potentially materialUrl/materialFile content) into the context composer (x-layout: contextComposer, primaryField materialText), where that text is not authored by the operating user.