agentforce-observe

Warn

Audited by Snyk on Jun 29, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from production user conversations is ingested into the agent’s LLM context via the STDM path: getConversationDetails() queries ssot__AiAgentInteractionMessage__dlm.ssot__ContentText__c (user “Input” and agent “Output” messages) and returns it as JSON, which the skill then uses for issue diagnosis/classification and presentation to the LLM.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 29, 2026, 01:58 PM
Issues
1
Security Audit — snyk — agentforce-observe