figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configures a connection to the official Figma MCP server at https://mcp.figma.com/mcp and uses the standard @figma/code-connect package for developer handoff.
  • [COMMAND_EXECUTION]: Provides instructions for the codex platform CLI to manage MCP server connections and user authentication.
  • [DATA_EXFILTRATION]: Downloads design assets, screenshots, and metadata from Figma nodes using authenticated API calls via the MCP server, which is the primary intended behavior of the skill.
  • [PROMPT_INJECTION]: The skill ingests data from Figma API responses, creating a potential surface for indirect prompt injection from design node content.
  • Ingestion points: Metadata and node properties retrieved via get_design_context and get_metadata (SKILL.md).
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: Includes create_node, update_node (SKILL.md), and local project file writes for code generation.
  • Sanitization: No content sanitization described for external data retrieved from Figma.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 01:52 PM