The Agent Skills Directory

[SAFE]: The skill facilitates communication with the official Figma MCP server at mcp.figma.com. This is a well-known service, and the network operations are limited to authenticated API requests for design data and assets.
[INDIRECT_PROMPT_INJECTION]: The skill processes external design data from Figma, which presents a potential surface for indirect prompt injection if malicious instructions were hidden within Figma design layers. This is documented as a functional risk factor inherent to the skill's purpose.
Ingestion points: External data is ingested through the get_design_context, get_metadata, and get_variable_defs tools in references/figma-tools-and-prompts.md.
Boundary markers: The skill does not explicitly define boundary markers or instruct the agent to ignore instructions embedded within the Figma node data.
Capability inventory: The skill provides the agent with the ability to inspect designs and translate them into local source code (React + Tailwind).
Sanitization: No specific sanitization or validation of the remote design content is required by the skill instructions.

figma