telnyx-voice-gather-java

Warn

Audited by Snyk on Mar 27, 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 clearly ingests untrusted, third‑party user content: SKILL.md documents starting an AI assistant and AI-powered gathers that process caller speech and message_history (Start AI Assistant, Gather using AI, webhooks like CallAIGatherPartialResults/CallAIGatherEnded) and also accepts external audio via audio_url/invalid_audio_url in gather_using_audio, all of which the agent is expected to read/interpret and can materially influence call actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 27, 2026, 01:02 AM
Issues
1