OpenAI Whisper
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill metadata includes an installation step using the Homebrew package manager to download 'openai-whisper'. This is a well-known service providing a verified package from a trusted organization.
- [COMMAND_EXECUTION]: The skill provides instructions for executing the 'whisper' command-line tool. These commands are standard for the tool's functionality and process local files as intended.
- [SAFE]: No malicious patterns, prompt injections, or unauthorized data exfiltration attempts were detected. The skill's functionality is consistent with its stated purpose of local transcription.
Audit Metadata