The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data provided by the user, such as Markdown, drafts, CSV, or Excel files, to generate the prototype content.
Ingestion points: instructions in SKILL.md and the 'How it works' section in example.html suggest that the agent should ingest external content provided by the user.
Boundary markers: The skill does not define specific delimiters or instructions to help the agent distinguish between legitimate data and malicious commands embedded within the input.
Capability inventory: The skill's primary capability is generating HTML and CSS code based on user-provided data.
Sanitization: No explicit sanitization or validation logic is defined in the skill's instructions for the agent to apply to external data.
[EXTERNAL_DOWNLOADS]: The example prototype references and downloads resources from well-known technology services.
Loads the Tailwind CSS library from cdn.tailwindcss.com to provide styling for the prototype.
Fetches typography resources from Google Fonts (fonts.googleapis.com).

prototype-web