The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from user briefs and an injected DESIGN.md file to inform its prototype generation.
Ingestion points: The skill reads the user's brief and the DESIGN.md configuration file to determine brand, value proposition, and design styles.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the prompt interpolation logic.
Capability inventory: The skill is restricted to generating static HTML and CSS artifacts. It does not possess capabilities for command execution, file system writes (outside of the artifact), or arbitrary network requests.
Sanitization: There is no explicit sanitization of the input data, but the lack of executable capabilities significantly limits the risk of exploitation.
[EXTERNAL_DOWNLOADS]: The provided example implementation references external resources from well-known service providers.
Evidence: The HTML template fetches font files and styles from fonts.googleapis.com and fonts.gstatic.com. These are recognized as safe, well-known services for web assets.

gamified-app