The Agent Skills Directory

[SAFE]: The skill provides utility scripts for common UX tasks such as checking color contrast (scripts/contrast-check.py) and displaying responsive breakpoints (scripts/responsive-breakpoints.sh). These scripts perform local calculations or output static information and do not perform network operations or access sensitive system files.
[SAFE]: The documentation extensively references official accessibility standards (WCAG 2.1 AA) and provides legitimate links to established testing tools and organizations (WebAIM, W3C, Deque, etc.).
[INDIRECT_PROMPT_INJECTION]: The skill identifies a standard attack surface where it processes external data (requirements, PRDs, and user stories) to generate design artifacts.
Ingestion points: Requirements documents and PRDs are read during the initial phase of the design workflow (noted in SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands within external documents are defined in the instructions.
Capability inventory: The agent has access to Write, Edit, and Bash tools, which are used to generate documentation and run local helper scripts.
Sanitization: No explicit sanitization or validation of external input content is performed before processing.

ux-designer