The Agent Skills Directory

[SAFE]: The skill contains no malicious code, remote execution patterns, or attempts to exfiltrate data. It strictly focuses on providing instructions for design aesthetics and UI hierarchy.
[PROMPT_INJECTION]: No attempts to bypass safety filters or override system instructions were found. The use of 'MANDATORY' or 'CRITICAL' instructions is limited to design best practices.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests brand colors and design context. However, the skill does not possess exploitable capabilities such as file system writes or network access, and it uses standard human-in-the-loop tool calls (AskUserQuestion).

colorize