The Agent Skills Directory

[PROMPT_INJECTION]: Indirect Injection Surface. The skill reads multiple local files, such as personas, design principles, and hypotheses, to generate prototype code. While these are local documentation files, if they were to contain malicious instructions, the agent could potentially execute them during the code generation process.
Ingestion points: Relevant project files including docs/product/design-principles.md, docs/product/personas/, and docs/discovery/hypotheses/.
Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the ingested file content.
Capability inventory: The skill is capable of writing new HTML files to the docs/discovery/prototypes/ directory.
Sanitization: There is no explicit sanitization step for the content read from documentation files before it is used in the generated output.
[EXTERNAL_DOWNLOADS]: The skill generates HTML files that reference external resources from well-known services.
Details: The prototypes are instructed to use Tailwind CSS and Google Fonts via their respective official CDNs. These are trusted technology providers and represent standard web development practices.

prototype-guide