voice-ai-development
Warn
Audited by Snyk on Aug 8, 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 the “Vapi Voice Agent” webhook flow, the runtime ingests outsider-authored free text from the caller (event["transcript"]) and passes it into the assistant conversation (end-of-call transcript is saved and would typically be used as user input).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata