figma-code-connect

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation and use of the official @figma/code-connect library from the NPM registry, which is standard for this vendor workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes component properties from Figma URLs which constitutes an external data ingestion surface.
  • Ingestion points: Figma component properties, variants, and text content are retrieved via the get_context_for_code_connect tool as described in SKILL.md.
  • Boundary markers: The skill explicitly requires the use of figma.code tagged template literals to wrap all generated code snippets, which serves to structurally isolate data from code.
  • Capability inventory: The skill has the capability to read project configuration files (figma.config.json, tsconfig.json) and write .figma.ts template files to the local file system.
  • Sanitization: Data retrieved from Figma is accessed through specific API methods like instance.getString and instance.getEnum which treat the values as static data types rather than executable instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:08 AM
Security Audit — agent-trust-hub — figma-code-connect