figma-to-react

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for a legitimate developer workflow, focusing on the accurate transformation of design data into production-ready code using platform-provided tools.
  • [EXTERNAL_DOWNLOADS]: The skill references Google Fonts (fonts.googleapis.com and fonts.gstatic.com), which are well-known services, to ensure that typography in the generated components matches the source design precisely.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its core function of processing external design data.
  • Ingestion points: External design data retrieved via mcp__figma__get_metadata and mcp__figma__get_design_context (SKILL.md).
  • Boundary markers: Absent; there are no specific delimiters or instructions to treat the incoming Figma data as untrusted content separate from the agent's instructions.
  • Capability inventory: The skill allows for the generation of complex React and Next.js components, involving significant code synthesis capabilities.
  • Sanitization: Absent; the skill does not include steps to sanitize or filter the metadata or design context retrieved from the Figma API before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:20 AM
Security Audit — agent-trust-hub — figma-to-react