The Agent Skills Directory

[SAFE]: The skill guides the agent in using the Figma MCP server to retrieve design specifications like colors, typography, and layout from Figma files.
[SAFE]: Installation instructions refer to the official Figma domain (mcp.figma.com), which is a well-known and trusted service for this context.
[SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected.
[SAFE]: The skill includes practical guidelines for handling screenshot size limits and efficiently researching components to minimize context window usage.
[SAFE]: The skill possesses a data ingestion surface through Figma tools (get_metadata, get_design_context) but lacks any dangerous capabilities (exec, eval, subprocess) to exploit. Boundary markers and sanitization are absent, which is typical for this type of research tool.

figma-researcher