skills/terminalskills/skills/whisper/Gen Agent Trust Hub

whisper

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads model weights and code from well-known and trusted sources including GitHub (ggerganov/whisper.cpp) and Hugging Face (pyannote/speaker-diarization-3.1). These are standard practices for AI model deployment.
  • [COMMAND_EXECUTION]: The instructions include standard package installation commands (pip install) and build commands (make) for the Whisper environment. These are necessary for the skill's stated purpose of transcribing audio.
  • [CREDENTIALS_UNSAFE]: The skill mentions using an OpenAI API key and a Hugging Face token. It correctly uses placeholders like 'sk-...' and 'hf_YOUR_TOKEN' rather than hardcoding actual secrets, following safe development practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 06:31 AM