The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python scripts to automate media tasks by calling system binaries (ffmpeg, ffprobe, magick, mogrify). These calls are implemented using subprocess.run() with argument lists, effectively mitigating shell injection risks by avoiding the use of shell=True and string concatenation for command building.
[INDIRECT_PROMPT_INJECTION]: The utility processes external multimedia files and extracts metadata (e.g., resolution, bitrate via ffprobe). While this provides an entry point for untrusted data, the skill does not interpolate these values into agent instructions in a way that could lead to prompt injection. The ingestion point is limited to technical metadata, and the capability inventory is restricted to secure media processing calls.
[SAFE]: The skill primarily serves as a wrapper for well-known, legitimate media processing utilities. All documented examples and scripts align with the stated purpose of the skill, with no evidence of obfuscation, data exfiltration, or persistence mechanisms.

media-processing