The Agent Skills Directory

[SAFE]: The skill is a legitimate utility for processing broadcast media captions and does not exhibit any malicious behavior.
[COMMAND_EXECUTION]: The Python helper script scripts/cc.py uses subprocess.run with list arguments to execute ffmpeg and ccextractor. This implementation follows security best practices by avoiding shell execution and properly handling argument separation, which prevents command injection vulnerabilities from potentially malicious file paths or user-supplied names.
[EXTERNAL_DOWNLOADS]: The skill references external tools such as ffmpeg and ccextractor. The instructions correctly direct the user to install these via trusted system package managers like Homebrew or APT. No automated, hidden, or unverified remote code downloads are performed by the skill itself.
[DATA_EXFILTRATION]: There are no network-related commands or code patterns that would indicate data exfiltration. All operations are local to the media files provided by the user, and no sensitive credentials or system files are accessed.

ffmpeg-captions