investigating-agentforce-d360

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

• Third-party content exposure detected (medium risk: 0.30). In the fetch_dc.py → dc.py Data Cloud query waterfall, outsider-provided free text can be submitted via session discovery filters (e.g., discover_sessions.py --grep matching ssot__AiAgentInteractionMessage__dlm.ssot__ContentText__c LIKE '%...%') and then the resulting Data Cloud rows (which include conversation/prompt text) are ingested and rendered in later stages.