The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions for generating UI components. It does not involve the execution of shell commands, external package installations, or access to sensitive file paths such as credentials or environment variables.
[INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided descriptions to guide code generation, creating a surface for indirect prompt injection.
Ingestion points: User descriptions provided through the $ARGUMENTS parameter in SKILL.md.
Boundary markers: There are no specific delimiters or instructions defined to isolate user input from the generation logic.
Capability inventory: The skill involves writing generated code to the local file system at project-specific paths (e.g., src/components/ui/).
Sanitization: The skill does not implement sanitization or validation for the input description.

ui-component