openai-whisper

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the Homebrew package manager to install the openai-whisper formula and downloads official machine learning models from OpenAI's infrastructure during its first run.
  • [COMMAND_EXECUTION]: Instructs the agent to execute the whisper CLI for processing audio files, including options for model selection, translation, and output formatting.
  • [DATA_EXPOSURE]: Accesses user-specified local audio files for the purpose of transcription; no malicious file access, credential harvesting, or data exfiltration patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — openai-whisper