Figma Implement Design

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Figma-to-code workflow that uses Figma MCP and OAuth access, with no hidden scripts or unrelated behavior found.

Install this only if you are comfortable connecting Codex to Figma MCP and authorizing Figma access. Use it for designs you intend the agent to inspect and implement, and review any downloaded assets and code changes before committing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill explicitly tells the agent to download and directly use assets from the Figma MCP server, including localhost-served assets, without requiring user awareness or confirmation about network access and local resource retrieval. While this is part of the intended workflow, it can still cause unintended access to local or remote resources and normalize blind trust of externally supplied asset URLs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal