figma-code-connect-components

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection Surface: The skill processes external metadata from Figma components and reads local source code files to suggest mappings. As with any skill that ingests external data, there is a potential surface for indirect instructions to be embedded in component names or code comments, though the skill's capabilities are focused on mapping rather than arbitrary execution.
  • Local Script Execution: A Python script (normalize_node_id.py) is included to convert Figma node identifiers between URL and tool formats. This script performs basic string manipulation and does not involve risky operations like network access or dynamic code evaluation.
  • External Service Integration: The skill connects to the official Figma MCP server (mcp.figma.com) to retrieve design data. This communication is restricted to the intended purpose of the skill and uses the established Figma infrastructure.
  • File System Access: The skill searches for component files in common project directories (e.g., src/components/). This access is necessary for its primary function and is guided by specific user-provided context regarding the project structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 04:51 PM