ai-voiceover-edge-tts
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the edge-tts Python package and the ffmpeg system utility. These are standard tools for text-to-speech and audio processing.
- [COMMAND_EXECUTION]: The script scripts/tts_edge.py invokes ffmpeg and ffprobe using subprocess.run and subprocess.check_output with argument lists. This implementation avoids shell injection risks and is used solely for legitimate audio format conversion and metadata extraction.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text and JSON data for voice synthesis.
- Ingestion points: Text input and storyboard.json data processed in scripts/tts_edge.py.
- Boundary markers: Instructions in SKILL.md guide the LLM to treat inputs as data for conversion.
- Capability inventory: File system writing (audio and JSON) and network access for TTS API calls.
- Sanitization: Ingested data is used as text for synthesis and is not processed in an executable context.
Audit Metadata