alicloud-ai-audio-cosyvoice-voice-clone

Warn

Audited by Snyk on Mar 11, 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). The skill explicitly requires and submits a public audio URL for enrollment (see SKILL.md's "Provide a public audio URL for the enrollment sample", the API "url"/voice_sample_url field in references/api_reference.md, and scripts/prepare_cosyvoice_clone_request.py), so it ingests arbitrary, untrusted third‑party audio that directly influences voice-clone creation and subsequent TTS behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 03:27 AM