The Agent Skills Directory

Command Execution via FFmpeg: The skill uses subprocess.run to invoke ffmpeg and ffprobe for video processing. Technical review confirms it correctly passes arguments as a list rather than a shell string, which prevents command injection vulnerabilities.
Safe YAML Parsing: Manifest files are processed using yaml.safe_load(). This is a recommended security practice that prevents arbitrary code execution during the deserialization of user-supplied data.
Configurable Tool Paths: The implementation allows users to specify the path to ffmpeg and ffprobe via environment variables (FFMPEG_COMMAND, FFPROBE_COMMAND). This is a standard feature for developer tools that accommodates diverse installation environments without introducing safety risks.
Secure Dependency Management: The skill utilizes uv for environment synchronization and dependency resolution, which is a modern and reliable tool for maintaining a secure and consistent execution environment.

demo-video