build-voice-agent
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The required runtime workflow is an inbound phone call via Twilio/Telnyx WebSocket where the caller’s spoken content is transcribed and fed into the agent’s LLM context; this is outsider-authored free text (the caller) entering through the carrier→STT→LLM path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata