openai-whisper

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides installation metadata to fetch the 'openai-whisper' package via Homebrew, a well-known package manager. It also notes that the tool downloads model weights from OpenAI's servers upon its first execution, which is standard behavior for this software.
  • [DATA_EXPOSURE]: The skill performs local audio transcription and translation. It accesses user-specified audio files and writes text outputs to the local filesystem without any evidence of data exfiltration or unauthorized access to sensitive system files.
  • [SAFE]: No evidence of prompt injection, obfuscation, persistence mechanisms, or malicious command execution was found within the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:07 AM