The Agent Skills Directory

[COMMAND_EXECUTION]: The skill core functionality relies on executing shell commands for image processing and file cleanup using tools such as magick, vtracer, svgo, and rm as defined in SKILL.md.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by interpolating user-provided file paths directly into shell commands without sanitization.
Ingestion points: External inputs INPUT_PNG and OUTPUT_SVG are used to build command strings in SKILL.md.
Boundary markers: No delimiters or safety warnings are present to isolate the interpolated variables from the surrounding shell command logic.
Capability inventory: The skill performs multiple subprocess calls (magick, vtracer, npx svgo, rm) as documented in SKILL.md.
Sanitization: The skill does not perform any validation, escaping, or sanitization of the file paths before they are executed in the shell environment.

lovstudio-png2svg