text-to-speech

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill's behavior matches its described purpose of autonomous text-to-speech generation.
  • [EXTERNAL_DOWNLOADS]: Fetches machine learning models from HuggingFace and utilizes official TTS APIs from OpenAI, Microsoft (edge-tts), and Google (gTTS). These sources are well-known and trusted services.
  • [COMMAND_EXECUTION]: Employs subprocess.run to interact with ffmpeg, ffprobe, and espeak-ng for audio processing, synthesis, and metadata extraction. These system calls use controlled parameters intended for media handling.
  • [PROMPT_INJECTION]: While the skill ingests untrusted text data, it includes a clean_for_tts function using regex to strip markdown formatting and symbols, providing a sanitization layer for the audio synthesis engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 05:35 AM