The Agent Skills Directory

[SAFE]: No security issues detected. The skill's instructions are focused on UI design generation.
[DATA_EXPOSURE]: The skill reads existing theme files to maintain project consistency, which is a standard design workflow and does not involve accessing sensitive system credentials, private configuration files, or environment secrets.
[PROMPT_INJECTION]: The skill processes existing design files which could theoretically serve as an indirect prompt injection surface. However, the risk is mitigated as the skill manifest does not request access to dangerous tools (such as network access or shell execution), and its primary function is to generate static code blocks for the user.

design-tokens