agentforce-d360-analyze

Warn

Audited by Snyk on Jun 26, 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). At runtime, render_dc.py (opt-in --show-prompts) reads outsider-authored free text from Data Cloud audit rows—specifically GenAIGatewayRequest__dlm.prompt__c (user/assistant prompt content) and GenAIGeneration__dlm.responseText__c—which are then unescaped and embedded verbatim into the agent’s LLM context via the rendered markdown/prompt display path.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 26, 2026, 12:31 PM
Issues
1
Security Audit — snyk — agentforce-d360-analyze