kokoro-tts

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely educational and instructional, focusing on the usage of a legitimate open-source text-to-speech model (Kokoro).
  • [EXTERNAL_DOWNLOADS]: The skill references official repositories and package registries (GitHub, Hugging Face, PyPI, NPM) for legitimate dependencies and documentation. All external sources are well-known services or project repositories relevant to the skill's purpose.
  • [COMMAND_EXECUTION]: Code examples provided are for local development and integration using standard libraries (e.g., Python's 'kokoro' and 'soundfile'), with no evidence of malicious command execution, privilege escalation, or persistence mechanisms.
  • [DATA_EXFILTRATION]: No data exfiltration patterns were found; the skill explicitly emphasizes privacy-constrained pipelines and offline/on-device execution as primary use cases.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:52 PM
Security Audit — agent-trust-hub — kokoro-tts