agentforce-d360-analyze

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

• Third-party content exposure detected (low risk: 0.10). Skill fetch_dc.py reads and LLM-renders first-party Data Cloud STDM/GenAI DMO rows for a specified Agentforce session (e.g., gateway_request.prompt__c, generations.responseText__c, messages.ssot__ContentText__c), but those texts are not authored via an outsider-writable submission path that the workflow monitors without the user first selecting a specific session id.