The Agent Skills Directory

[SAFE]: No security issues detected. The skill provides instructions for the agent to generate React UI components based on local design tokens and conventions.
[DATA_EXFILTRATION]: No sensitive data exposure or exfiltration patterns identified. The skill only reads local project configuration files (e.g., CLAUDE.md, theme.css) for context, which is standard behavior for development-oriented tools.
[PROMPT_INJECTION]: The skill processes user-provided descriptions to generate code, which is a standard ingestion point for indirect instructions. Ingestion points: The skill takes user input via the $ARGUMENTS variable in the SKILL.md file. Boundary markers: None identified. Capability inventory: The skill is designed to read local files and write new React component files; it does not have network access or system-level execution capabilities. Sanitization: No explicit sanitization or filtering of the user description is performed before code generation. The impact of potential injection is limited by the skill's specific purpose and lack of sensitive capabilities.

ui-component