audio-transcription
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads machine learning models from the
mlx-communityorganization on Hugging Face using thehuggingface-hublibrary. Hugging Face is a well-known and established service for model distribution. - [COMMAND_EXECUTION]: The main script
transcribe-audio.pyusessubprocess.runto execute transcription tasks viauvx. The commands are constructed using argument lists rather than shell strings, which is a security best practice for preventing command injection. - [DATA_EXFILTRATION]: The skill manages temporary file storage in local
/private/tmp/directories for processing audio inputs and storing transcripts. These operations are confined to the local filesystem and do not involve unauthorized network transmission.
Audit Metadata