fountain-clip-producer
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on system binaries including
ffmpeg,ffprobe,yt-dlp,magick(ImageMagick), andfc-match(fontconfig) to process media files. These are invoked using Python'ssubprocess.runwith argument lists, which is the recommended method for executing external commands without invoking a shell. - [EXTERNAL_DOWNLOADS]: The skill fetches video and audio content from external sources like YouTube and the Fountain API via
yt-dlp. It also suggests downloading a 141 MBwhisper.cppmodel from a well-known repository on Hugging Face (huggingface.co/ggerganov/whisper.cpp) to enable word-level transcription during the preflight stage. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as episode transcripts and auto-generated captions. 1. Ingestion points: External transcripts and captions are read into the skill context via
modules/media/scripts/build-time-map.pyandmodules/captions/scripts/build-captions.py. 2. Boundary markers: No specific delimiters or 'ignore' instructions were found for the interpolated text data. 3. Capability inventory: The skill usessubprocess.runto callffmpeg,magick, andyt-dlpacross several modules (media, captions, overlays, framing). 4. Sanitization: Themodules/overlays/scripts/build-overlays.pyscript includes anescape_drawtextfunction designed to escape special characters before they are passed to FFmpeg filters, andbuild-captions.pyperforms text hygiene (faithful-clean) on word data.
Audit Metadata