voice

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill calls ElevenLabs STT (scripts/stt_elevenlabs.py) and the SKILL.md/references/architecture.md describe feeding those transcriptions into Claude (Team SendMessage / voice_bridge) as conversation turns, so untrusted third-party-produced transcripts can be read and acted on by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:57 AM