The Agent Skills Directory

[SAFE]: The skill's primary function is to generate Markdown documentation for design systems. It correctly references official documentation from a trusted source (Google) for its schema guidance.
[SAFE]: No suspicious patterns such as direct prompt injection, data exfiltration, or obfuscation were detected in the instructions or scripts.
[PROMPT_INJECTION]: The skill processes untrusted user inputs (images, descriptions, and code) to generate documentation, which represents an indirect prompt injection surface. 1. Ingestion points: Inputs are gathered from the conversation context, images, screenshots, and existing project files. 2. Boundary markers: No explicit delimiters or instructions are used to separate untrusted source content. 3. Capability inventory: The skill is capable of reading project files and writing Markdown. 4. Sanitization: No input sanitization is performed. Despite these factors, the risk is categorized as safe because the output is limited to static documentation.

create-design-md