The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected in the skill instructions or examples. The skill is designed to format user-provided data into specific Text UI and JSON structures for drawing tools.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled input (component properties like titles and body text) to generate visual output. While this is an inherent characteristic of UI generation tools, there is a theoretical surface where malicious instructions embedded in input properties could attempt to influence the agent's behavior. The risk is minimized by the use of strict output blocks and structural constraints.
[NO_CODE]: The skill consists entirely of markdown instructions and data templates. It does not include scripts, binaries, or instructions for the agent to install or execute external code.

tui-modal