fish-audio-tts

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical guide for the Fish Audio TTS platform. It correctly identifies official API endpoints (api.fish.audio) and documentation sources.
  • [COMMAND_EXECUTION]: Provides illustrative shell and Python code snippets for calculating costs and interacting with the REST/WebSocket APIs. These examples are transparent, use standard libraries, and are intended for legitimate developer use.
  • [EXTERNAL_DOWNLOADS]: References official model weights on Hugging Face and source code on GitHub for the OpenAudio/Fish-Speech project. These are legitimate resources provided for the self-hosting capability described.
  • [DATA_EXFILTRATION]: Documents the transmission of text and audio data to the Fish Audio service. This data flow is central to the skill's purpose and is performed via authenticated, official endpoints.
  • [PROMPT_INJECTION]: The skill does not contain instructions to bypass safety filters or override agent behavior. Conversely, it explicitly instructs the agent to enforce voice-cloning consent rules and legal compliance.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:52 PM
Security Audit — agent-trust-hub — fish-audio-tts