The Agent Skills Directory

[SAFE]: The skill functions as a logical router for design tasks. It does not utilize any platform tools, perform network requests, or interact with the file system. The instructions focus on decomposing user requests into structured text output.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user design requests (SKILL.md). While it lacks boundary markers or sanitization to prevent the agent from following instructions embedded in the design request, the skill has zero functional capabilities (no subprocess calls, file writes, or network operations), resulting in no technical security risk.

apere