The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references documentation and examples from trusted sources, including the official Lit library (lit.dev), MDN Web Docs (mozilla.org), and a demo repository on GitHub (ochorocho/lit_demo).
[COMMAND_EXECUTION]: Includes examples of rg (ripgrep) commands for searching project source code to identify existing custom elements and module registrations.
[INDIRECT_PROMPT_INJECTION]: The skill guides the creation of components that ingest data from backend endpoints and HTML attributes. While it recommends using Lit for templating (which handles escaping) and server-side permission checks, the ingestion of untrusted or external data represents a potential attack surface.
Ingestion points: Component attributes (e.g., endpoint) and JSON payloads from backend AJAX routes (specified in references/examples-and-howtos.md).
Boundary markers: None explicitly defined for the data returned by external routes.
Capability inventory: Network requests via fetch and AjaxRequest; dynamic element registration via customElements.define (specified in references/examples-and-howtos.md).
Sanitization: Employs Lit's html template literals for automatic escaping and advises manual escaping of Fluid output.

typo3-webcomponents