Security audit

Figma Design Tool Free

Security checks across malware telemetry and agentic risk

Overview

This Figma integration is mostly purpose-aligned, but it needs review because it combines external workspace access with broad execution and routing instructions that are not tightly scoped.

Review before installing. Only use this skill for Figma files and assets you are allowed to expose through MorphixAI/Figma APIs, avoid using it for unrelated document or file-conversion tasks, and treat the API key plus linked Figma account as persistent access that should be revoked when no longer needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Description-Behavior Mismatch

Medium

Confidence: 90% confidence
Finding: The skill is presented as a lightweight Figma integration, but its instructions include local command execution and network diagnostics, expanding behavior beyond the declared scope. Scope expansion is dangerous because users or agents may permit execution assuming only Figma API access, while the skill also nudges the agent toward host-level actions that can expose system information or normalize unnecessary command execution.

Context-Inappropriate Capability

Low

Confidence: 84% confidence
Finding: Including ping-based network diagnostics in a Figma design skill introduces unrelated system command behavior. Even if benign on its face, this broadens the operational surface and can condition an agent to run local commands not necessary for the business purpose, which is unsafe under least-privilege expectations.

Intent-Code Divergence

Medium

Confidence: 87% confidence
Finding: The document says the free version is read-only and does not support create actions, but later states that core execution supports 'create/query/export' operations. This contradiction can mislead an agent or user about the effective permission model, increasing the risk of unintended state-changing actions or unsafe assumptions during tool invocation.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger condition is much broader than the actual Figma-specific functionality, suggesting use for generic file processing, document conversion, format conversion, or content extraction. Overbroad routing criteria are risky because they can cause this skill to be selected in contexts where it is inappropriate, potentially sending unrelated data to external services or invoking unnecessary capabilities.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The description omits a clear warning that the skill accesses external Figma workspace data and routes requests through MorphixAI and Figma APIs. This is dangerous because users may not understand that potentially sensitive design metadata, comments, or asset requests leave the local environment and are handled by third-party services.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.