cartesia-tts

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script uses subprocess.run to invoke ffmpeg for audio conversion. Security is maintained by using a static list of arguments and sanitizing dynamic filenames with a regular expression, preventing shell injection.
  • [EXTERNAL_DOWNLOADS]: Audio data and voice metadata are retrieved from Cartesia's official infrastructure. These are expected network operations for a TTS skill.
  • [CREDENTIALS_UNSAFE]: While the skill accesses a local API key, it includes defensive networking logic to ensure credentials are never forwarded to third-party storage sites during HTTP redirects.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 05:02 AM