openai-whisper

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security concerns were identified. The skill is a standard wrapper for the OpenAI Whisper CLI tool and includes transparent metadata for installation via Homebrew.
  • [EXTERNAL_DOWNLOADS]: The skill informs the user that model weights are downloaded from OpenAI's official infrastructure to the local cache (~/.cache/whisper) upon first run, which is the expected and documented behavior for this utility.
  • [COMMAND_EXECUTION]: The instructions demonstrate standard usage of the 'whisper' command for audio processing using user-provided file paths and predefined CLI flags.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:08 AM
Security Audit — agent-trust-hub — openai-whisper