The Agent Skills Directory

[SAFE]: No security issues were detected. The skill provides styling functionality with clear human-in-the-loop confirmation steps and relies on local theme specifications and user input for formatting purposes. No network access, sensitive file access, or remote code execution patterns were found.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes theme files and user-provided descriptions. However, this is considered safe given the specific context of selecting colors and fonts. Ingestion points: Local files in the themes/ directory and user-provided descriptions for custom themes. Boundary markers: None explicitly defined. Capability inventory: Reading local files and modifying artifacts. Sanitization: None explicitly defined.

theme-factory