Skills
Navigate
skills/coco-research/coco/openai-whisper/Gen Agent Trust Hub

openai-whisper

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the whisper command-line utility and a local shell script {baseDir}/scripts/transcribe.sh to process audio files and generate transcripts.
  • [EXTERNAL_DOWNLOADS]: Downloads Whisper transcription models from official OpenAI resources to the local ~/.cache/whisper directory upon first execution of the local CLI mode.
  • [SAFE]: Utilizes trusted OpenAI API endpoints (api.openai.com) for cloud-based transcription tasks.
  • [SAFE]: Provides clear instructions for secure API key management using environment variables or configuration placeholders, avoiding hardcoded secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 05:23 AM