The Agent Skills Directory

[SAFE]: No security issues were detected. The skill's primary function is to provide stylistic metadata (colors, typography, spacing) for UI generation. The instructions are transparent and consistent with the stated purpose.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a bundled reference file to influence agent behavior.
Ingestion points: The agent is instructed to read references/DESIGN.md before generating any components.
Boundary markers: The skill includes explicit instructions to strictly match documented tokens and avoid falling back to generic defaults, which helps maintain consistency but does not act as a security boundary.
Capability inventory: The skill does not define or call any dangerous tools, shell commands, or network operations.
Sanitization: Not applicable, as the ingested content consists of static design tokens.

anthropic-brand