The Agent Skills Directory

[SAFE]: The skill provides comprehensive instructions and a helper script for performing advanced video operations such as masking, alpha merging, and channel surgery with FFmpeg.
[COMMAND_EXECUTION]: The skill uses ffmpeg and ffprobe to process media files. These commands are standard for the skill's stated purpose and do not involve shell injection vulnerabilities.
[REMOTE_CODE_EXECUTION]: The Python script scripts/compose.py executes ffmpeg using subprocess.run() with a list of arguments. This method is the secure standard for invoking external processes as it avoids the risks associated with shell interpolation.
[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected in the instructions.
[DATA_EXFILTRATION]: No network operations or sensitive file access patterns were found. The skill operates entirely on local media files provided by the user.
[OBFUSCATION]: The skill's instructions and code are clear, well-structured, and contain no hidden or encoded content.

ffmpeg-compose-mask