telnyx-voice-gather-curl

Warn

Audited by Snyk on Mar 16, 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's documentation explicitly describes starting an AI assistant (ai_assistant_start) and using "gather_using_ai" plus related webhooks (CallAIGatherEnded / CallAIGatherMessageHistoryUpdated / CallAIGatherPartialResults) which ingest caller speech and message_history (untrusted, user-generated content) that the assistant is expected to read/interpret and which can materially influence subsequent actions on the call.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 16, 2026, 10:34 AM
Issues
1