openai-whisper

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized data access patterns were identified in the skill instructions or configuration metadata.
  • [EXTERNAL_DOWNLOADS]: The skill's installation metadata specifies fetching the openai-whisper formula through the Homebrew package manager.
  • [EXTERNAL_DOWNLOADS]: The CLI tool is documented to download pre-trained machine learning models from OpenAI to the local ~/.cache/whisper directory during its first run.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:31 PM
Security Audit — agent-trust-hub — openai-whisper