The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes subprocess.run() within scripts/render_assembly.py and scripts/validate_collage.py to execute FFmpeg and ffprobe for video generation and metadata extraction. These scripts implement a safety mechanism named inside() and safe_asset() that uses path.relative_to to verify all file operations remain within the project directory, effectively preventing path traversal. Furthermore, the scripts cast all user-controllable numeric parameters from JSON configuration files to float or integer types before including them in FFmpeg command arguments or filter expressions.
[SAFE]: The skill does not contain any suspicious patterns related to data exfiltration, credential theft, or code obfuscation. Its primary functions are transparent and utilize well-known platform capabilities and local utilities.

editorial-collage-motion