voice-ai-development
Warn
Audited by Snyk on Nov 5, 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 required workflow involves voice-to-voice integration using external APIs (OpenAI, Vapi, Deepgram) where user speech is transcribed and passed into the agent workflow without an explicit pre-selection mechanism, presenting an indirect prompt injection risk.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata