observing-agentforce
Warn
Audited by Snyk on Jul 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In Phase 1 the skill queries Data Cloud STDM session traces for conversation messages/LLM prompts (user-authored input/output and prompt text) via
AgentforceOptimizeService.getConversationDetails()/getLlmStepDetails()and parses them into JSON for later LLM-based issue analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata