The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted user data such as documents and notes to generate HTML presentations, representing an indirect prompt injection surface. 1. Ingestion points: User-provided textual content described in SKILL.md. 2. Boundary markers: No explicit delimiters are specified to separate user content from instructions. 3. Capability inventory: The skill writes an HTML file (presentation.html) as its primary output. 4. Sanitization: No sanitization or escaping of the user content is mentioned before it is embedded in the HTML output.
[EXTERNAL_DOWNLOADS]: The skill references CSS and JS assets from well-known CDNs including jsDelivr and Unpkg to provide the Reveal.js framework and Lucide icons. These sources are recognized as reputable public services for web assets and are used according to the skill's intended functionality.

html-presentation