The Agent Skills Directory

[SAFE]: The skill instructions and documentation focus on providing creative and technical guidance for UI/UX design. No evidence of prompt injection, data exfiltration, or persistence mechanisms was found.
[INDIRECT_PROMPT_INJECTION]: As a tool designed to generate code and interfaces based on user requests, the skill possesses an inherent attack surface where untrusted user input could potentially include malicious instructions. However, this risk is mitigated by the skill's focus on design collaboration and the nature of the primary use case.
Ingestion points: User-provided design requirements, tone preferences, and functional constraints defined in the 'Design Thinking Protocol' section of SKILL.md.
Boundary markers: The skill does not define explicit delimiters to isolate user-provided context from the agent's core instructions.
Capability inventory: The skill generates React components and Tailwind CSS code, and it references the use of the playwright MCP for visual verification of generated interfaces.
Sanitization: There are no explicit instructions for the agent to sanitize or filter user-provided content before processing or interpolating it into the design output.
[EXTERNAL_DOWNLOADS]: The skill includes links to external documentation and resources from trusted organizations and well-known services, such as Anthropic's GitHub repository, the W3C Web Accessibility Initiative, Google Fonts, and official documentation for Tailwind CSS and Shadcn UI. These references are used for educational and configuration purposes and do not constitute a remote code execution risk.

bencium-innovative-ux-designer