mlx-whisper

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the mlx-whisper Python package and downloads pre-trained weights from the Hugging Face mlx-community organization. These are legitimate resources within the Apple Silicon machine learning ecosystem.
  • [PROMPT_INJECTION]: The skill processes external audio data which, when transcribed, could contain instructions designed to influence the agent (Indirect Prompt Injection surface). • Ingestion points: Audio file content via mlx_whisper.transcribe. • Boundary markers: Absent. • Capability inventory: Local file system read access for audio files and local Python code execution. • Sanitization: Absent.
  • [SAFE]: No evidence of obfuscation, data exfiltration, credential harvesting, or unauthorized privilege escalation was found. The skill's operations are consistent with its stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:07 AM