The Agent Skills Directory

[SAFE]: The skill's primary function is to generate design specifications (colors, typography, spacing) and save them to local files. It does not perform network operations (other than standard web search for inspiration if requested) or access sensitive system configuration.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes user-provided project context and reads existing token files (.planning/design/system/tokens.md) to guide its generation.
Ingestion points: User input regarding project context (Step 1) and existing design files (Constraint section in SKILL.md).
Boundary markers: No specific boundary markers or 'ignore' instructions are used when interpolating these inputs into the agent's logic.
Capability inventory: The skill has access to Write, Edit, and Bash tools, which are used to create design documents and project files.
Sanitization: No explicit sanitization of input data is performed. However, given the specific domain of design tokens, the risk of executable instruction injection is negligible.

design-intelligence