ai-voice-design

Warn

Audited by Snyk on Feb 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs ingesting user-supplied audio for voice cloning (e.g., "Upload audio" in the ElevenLabs Instant Clone flow and reference_audio="reference.wav" in the Qwen3-TTS examples), so it consumes untrusted user-generated content that the agent would process as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 13, 2026, 03:26 PM