whisper

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references established and reputable machine learning libraries (openai-whisper, transformers, torch, and faster-whisper) from official package registries.
  • [COMMAND_EXECUTION] (SAFE): Standard installation commands for system tools like ffmpeg and Python packages are provided as documentation; these are essential for the skill's purpose and are not part of any automated malicious script.
  • [DATA_EXFILTRATION] (SAFE): All audio processing is described as occurring locally, and no evidence was found of unauthorized network activity, data exfiltration, or the use of hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:48 PM