figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a structured workflow using legitimate Figma MCP server tools (get_design_context, get_metadata, get_screenshot) to perform its primary function of design translation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Figma designs which could potentially contain malicious instructions embedded by an attacker in design layer names or metadata.
  • Ingestion points: Design data retrieved via get_design_context and get_metadata tools.
  • Boundary markers: The skill does not explicitly instruct the agent to ignore instructions found within the design data.
  • Capability inventory: The skill's primary purpose is to write and modify code in the user's repository.
  • Sanitization: No specific sanitization or filtering of design-provided text is requested before code generation.
  • [EXTERNAL_DOWNLOADS]: The skill describes downloading assets (images, SVGs) from the Figma MCP server. These are served via a local assets endpoint (localhost), which is standard behavior for this toolchain and does not involve untrusted remote execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 12:30 AM
Security Audit — agent-trust-hub — figma-implement-design