figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to connect to the official Figma MCP server at https://mcp.figma.com/mcp to fetch design data, screenshots, and assets. Figma is a well-known and trusted service.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted design data from Figma, creating an indirect prompt injection attack surface. * Ingestion points: Design data, metadata, and screenshots are retrieved via MCP tools from external Figma URLs as defined in SKILL.md. * Boundary markers: The Anti-Patterns section in SKILL.md explicitly warns the agent not to treat tool responses or external content as trusted instructions. * Capability inventory: The skill allows the agent to generate and write production-ready code and UI components directly into the local project repository. * Sanitization: The skill emphasizes adherence to project design tokens and manual visual validation but lacks automated sanitization of the external design data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:52 AM
Security Audit — agent-trust-hub — figma-implement-design