skills/twilio/ai/twilio-voice-conversation-relay/Snyk

twilio-voice-conversation-relay

Warn

Audited by Snyk on May 8, 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 skill's SKILL.md shows the app receives untrusted ASR-transcribed caller speech via WebSocket "prompt" events (voicePrompt) and directly passes that content to an LLM (Step 2 / WebSocket Message Types), allowing third-party input to influence subsequent tool actions and responses.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

May 8, 2026, 04:08 PM

Issues

1

Security Audit — snyk — twilio-voice-conversation-relay