The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes React component templates that ingest untrusted data, creating a potential surface for indirect prompt injection if the rendered content is subsequently processed by an AI agent.
Ingestion points: React components such as ResponsiveCard (accepting title and description), ResponsiveNav (accepting items), and ResponsiveTable (accepting data) in SKILL.md process external data.
Boundary markers: The code snippets do not include explicit boundary markers or instructions to ignore embedded commands within the props.
Capability inventory: The skill does not include any dangerous capabilities; there are no subprocess calls, file-system write operations, network requests, or dynamic code execution (eval/exec) across any of the files.
Sanitization: No specific sanitization logic is provided in the snippets, as they rely on standard React rendering which provides basic XSS protection but not semantic instruction filtering.
[SAFE]: All external links and resources point to well-known documentation and educational services such as MDN Web Docs, Tailwind CSS, W3C, and Smashing Magazine. The mentioned Node.js package is a standard plugin from a well-known service (Tailwind CSS).

responsive-design