agentforce-eval-harness
Warn
Audited by Snyk on Jun 16, 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). The REQUIRED workflow is to “collect real transcripts from UAT or production (anonymized)” and replay them into the harness, so at runtime the agent/LLM context can include outsider-authored free-form user messages from other people/channels.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata