skills/noizai/skills/speech-to-text/Gen Agent Trust Hub

speech-to-text

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a Python script scripts/stt.py to handle the transcription workflow, file validation, and configuration management.
  • [EXTERNAL_DOWNLOADS]: The skill requires the standard requests Python library for facilitating HTTP communication with the service API.
  • [DATA_EXFILTRATION]: Audio files are uploaded to the official vendor endpoint at https://noiz.ai/v1/speech-to-text for processing. This network activity is documented and necessary for the core functionality of the skill.
  • [SAFE]: The skill implements secure credential storage by saving the API key in ~/.config/noiz/api_key with restricted filesystem permissions (0600), ensuring that only the owner can access the secret.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 09:29 PM