audio-voice
Warn
Audited by Snyk on Mar 25, 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 downloads and loads models from the public HuggingFace repository on first run (see "模型自动下载" in SKILL.md and the DEFAULT_MODEL values in scripts/asr_transcribe.py and tts_speak.py), meaning it ingests third-party user-hosted model artifacts that can influence outputs and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata