The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard shell commands, specifically grep and cat, to search for color hex codes, CSS variables, and Tailwind CSS patterns within the local project directory. These operations are restricted to relevant file types and are essential for the skill's primary function as an audit tool.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads and analyzes content from user-provided source files. * Ingestion points: Code snippets are ingested from files with .css, .scss, .tsx, .jsx, .svelte, and .html extensions during the scanning process defined in SKILL.md. * Boundary markers: The skill does not explicitly use boundary markers or delimiters when processing the extracted code snippets. * Capability inventory: The skill can read local files and has instructions to modify source files to apply design fixes. * Sanitization: There is no explicit sanitization of the content extracted from the codebase before it is presented to the agent for analysis.
[EXTERNAL_DOWNLOADS]: The documentation in references/wcag.md suggests the use of the contrast-ratio utility via npx, which involves fetching the package from the official NPM registry.

web-design-guidelines