voice-ai

Warn

Audited by Snyk on Mar 22, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill ingests untrusted user-generated caller audio via Twilio Media Streams (see the /voice/stream and /voice/media-stream WebSocket handlers in reference/twilio-webhooks.md), sends it to Deepgram STT for transcription, and feeds the resulting text into the Groq LLM to drive actions/responses—so external third-party content can indirectly inject instructions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 06:51 PM
Issues
1