voice-ai
Warn
Audited by Snyk on Sep 17, 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). The workflow builds a real-time voice assistant handling phone calls via Twilio and speech-to-text input (Deepgram STT), which ingests arbitrary caller-submitted spoken free text without prior selection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata