fluidaudio

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's workflow explicitly auto-downloads and loads models from public HuggingFace repositories (see "Models auto-download from HuggingFace" in references/infrastructure.md and the Quick Start) and allows redirecting the model registry URL (ModelRegistry.baseURL), meaning untrusted third-party model files from the open web are fetched and then directly influence ASR/diarization/TTS outputs used at runtime.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 03:17 PM
Issues
1