agentforce-test
Warn
Audited by Snyk on Aug 7, 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 Mode C2 (live adversarial probing), the workflow sends user-supplied adversarial payload strings via
sf agent preview send --utterance "<payload>", and the agent runtime ingests that free text at conversation time.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata