figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A comprehensive security audit of the skill instructions and configuration files revealed no malicious intent or security vulnerabilities. The implementation steps align with official Figma developer guidelines.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8) because it processes design metadata from external Figma URLs provided by the user. This is an inherent part of the design-to-code workflow and is assessed as low risk.
  • Ingestion points: Design data and node metadata fetched via the get_design_context tool (SKILL.md).
  • Boundary markers: None specified for the Figma design payload.
  • Capability inventory: The agent is tasked with generating and writing component code to the local filesystem.
  • Sanitization: No explicit sanitization of node property values is mentioned before code generation.- [EXTERNAL_DOWNLOADS]: The skill interacts with the official Figma MCP endpoint (https://mcp.figma.com/mcp) for tool definitions and asset retrieval. These references are considered safe as they target a well-known, trusted service.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:17 PM