The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script scripts/expr.py that executes the ffmpeg command-line tool. It uses subprocess.run with a list of arguments, which is a secure way to call external processes and prevents shell injection.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. 1. Ingestion points: Expressions and file paths provided as arguments to the scripts/expr.py script. 2. Boundary markers: None present. 3. Capability inventory: Execution of ffmpeg for file processing (read/write) via subprocess.run in scripts/expr.py. 4. Sanitization: The script uses argparse and list-based subprocess calls to prevent shell escape, though it does not restrict the files FFmpeg can access.

ffmpeg-geq-expr