The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/mediainfo.py uses subprocess.run to call the mediainfo binary. The implementation uses a list of arguments, which prevents shell command injection.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via media file metadata. 1. Ingestion points: media files processed by mediainfo (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: subprocess execution of mediainfo (scripts/mediainfo.py); no file-write or custom network capabilities. 4. Sanitization: uses list-based subprocess arguments to prevent command injection.
[EXTERNAL_DOWNLOADS]: The documentation suggests installing the mediainfo dependency via official system package managers like apt-get and brew.

media-mediainfo