openai-whisper
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses Homebrew, a well-known and trusted service, to install the official 'openai-whisper' package.
- [SAFE]: Operations are focused on local audio processing, with model downloads occurring from official OpenAI sources to the local cache directory.
- [SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or malicious command execution were detected in the skill's instructions or metadata.
Audit Metadata