xiaoyuzhou-podcast-transcriber
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches podcast audio files from the official Xiaoyuzhou media CDN (media.xyzcdn.net) based on user-provided links.
- [EXTERNAL_DOWNLOADS]: Downloads pre-trained speech-to-text models from Alibaba's ModelScope repository (iic/speech_paraformer-large...). These are established, well-known models for Chinese transcription.
- [COMMAND_EXECUTION]: Uses system utilities including curl, grep, and ffmpeg to retrieve HTML content and process audio files (format conversion and chunking).
- [COMMAND_EXECUTION]: Dynamically generates and executes a Python script (transcribe_chunked.py) within a virtual environment to run the transcription models locally.
Audit Metadata