ClawHub
Back to skill

Security audit

Figma设计工具v2

Security checks across malware telemetry and agentic risk

Overview

This Figma skill discloses useful design-workspace functions, but it also asks for broad local read/write and command execution authority without tight scoping.

Review carefully before installing. Use a least-privileged Figma token or account, avoid exposing sensitive team files unless needed, and keep local command execution or file writes disabled or sandboxed unless you explicitly intend to allow them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill is presented as a Figma integration, but it explicitly advertises generic system command execution and includes the powerful exec tool in metadata. That creates a dangerous scope expansion: prompts intended for design/file operations could be translated into arbitrary local command execution, enabling host compromise, data exfiltration, or abuse of available credentials if the agent runtime permits execution.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The documentation does not clearly warn users that the skill can access and potentially modify Figma workspace data, including comments and other project artifacts. Missing consent and transparency around workspace-affecting actions increases the chance of unintended data exposure or unauthorized modifications, especially in collaborative design environments.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.