figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [External Data Ingestion]: The skill fetches design specifications and assets from Figma URLs via an official MCP server (mcp.figma.com). This is central to the skill's operation and uses well-known service infrastructure.
  • [Indirect Prompt Injection Surface]: The skill ingests data from external Figma nodes to generate application code. This presents a potential surface where malformed or specially crafted design data could attempt to influence the code generation process.
  • Ingestion points: Design data is fetched via get_design_context and get_metadata in SKILL.md based on user-provided URLs.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the design data context.
  • Capability inventory: The skill is designed to write production-ready code into the local repository.
  • Sanitization: The instructions do not specify sanitization or validation of the design data content before it is used for code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:24 PM
Security Audit — agent-trust-hub — figma-implement-design