The Agent Skills Directory

[COMMAND_EXECUTION]: The bundled scripts scripts/media_inventory.py and scripts/video_qc.py use the subprocess module to call ffmpeg and ffprobe. Technical analysis confirms that commands are executed using argument lists rather than shell strings, which effectively prevents shell injection vulnerabilities. The scripts allow specifying binary paths via environment variables or command-line flags, which is a standard configuration practice.
[DATA_EXFILTRATION]: No network-reaching code or exfiltration patterns were detected. The skill is designed for local media processing, and the scripts only output metadata to the local console or specified local files.
[SAFE]: The workflow instructions emphasize protecting original media and following a structured, multi-gate review process. No prompt injection, obfuscation, or persistence mechanisms were found.

edit-video-story