The Agent Skills Directory

[SAFE]: The skill contains legitimate architectural guidance, design system templates, and a theme management JavaScript class. All code snippets are static and focused on user experience foundations.\n- [COMMAND_EXECUTION]: The skill instructions include shell commands like cat and grep used to read project configuration and goals from the local ai/memory-bank/ directory. These are standard contextual information gathering steps and pose no inherent risk.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from project files (e.g., ai/memory-bank/site-setup.md), which constitutes an indirect prompt injection surface. However, the skill lacks dangerous capabilities such as network exfiltration or remote code execution, making this surface low-risk and within normal operational parameters.

ux-architect