fish-audio-tts

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a guide for using the Fish Audio API. It correctly identifies the need for API keys to be stored in environment variables and provides links to the official Fish Audio service for key management and documentation.- [INDIRECT_PROMPT_INJECTION]: The skill describes tools that take user-provided text to generate audio. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the text to be spoken. Ingestion points: The text parameter in the FishAudioTTS.execute and TTSSelector.execute examples in SKILL.md. Boundary markers: None identified in the provided examples. Capability inventory: The skill facilitates writing generated audio to the local file system via the output_path parameter. Sanitization: No input sanitization is mentioned in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 01:56 AM