The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which may contain embedded instructions designed to influence the agent's behavior.
Ingestion points: The workflow involves reading local variable collections, text styles, and searching design system libraries in existing Figma files. It also references processing content from figma.com links and user-uploaded inspiration images.
Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between design data and potentially malicious instructions embedded within Figma layers, component names, or image metadata.
Capability inventory: The skill uses tools for Figma interaction (use_figma, search_design_system) which allow the agent to create nodes, modify styles, and execute SVG imports via createNodeFromSvg.
Sanitization: The skill lacks instructions for validating or sanitizing strings, names, or values retrieved from external Figma files or images before using them in subsequent tool calls or design operations.

figma-designer