Back to skill

Security audit

Figma设计工具包(专业版)

Security checks across malware telemetry and agentic risk

Overview

This Figma skill is not clearly malicious, but it asks for broad command and file access while handling Figma tokens and design data through under-scoped third-party tooling.

Review this skill before installing. Only use it with Figma files you are allowed to process, prefer a least-privilege token supplied through environment variables, avoid pasting real tokens into examples or config files, and confirm where generated code, exported assets, logs, and webhook callbacks will go.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Intent-Code Divergence

Medium
Confidence
98% confidence
Finding
The skill's own security guidance says tokens should come from environment variables, yet the example instantiates the engine with a literal placeholder token string. Even though it is a placeholder, this normalizes hardcoding secrets and can lead users to paste real Figma tokens directly into source files, where they may be committed or logged.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation guidance is overly broad, suggesting use whenever the user wants to improve efficiency, automate workflows, or handle batch processing. In a skill with read/exec/write capabilities and external service access, vague routing language can cause accidental invocation on unrelated tasks, expanding exposure of local files, commands, and design data beyond user intent.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The example trigger phrase for converting a Figma design to a React component is generic enough to overlap with normal conversation and routine coding requests. Because the skill can execute commands and write outputs, ambiguous triggers increase the risk of unintended tool activation and unnecessary data processing.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill supports file reads, writes, and asset exports, but the description does not clearly foreground that local files and exported artifacts may be created or modified. Users may invoke the skill expecting analysis only, while it can materially alter the workspace by writing generated code or downloaded assets.

Missing User Warnings

High
Confidence
97% confidence
Finding
The documentation requires a Figma personal access token and an external npm-based adapter, but it does not clearly warn that tokens and design data may be transmitted to external services and third-party command-line tooling. This is especially dangerous in a design-to-code skill because Figma files often contain proprietary product designs, internal naming, and unreleased assets.

External Transmission

Medium
Category
Data Exfiltration
Content
class FigmaDesignEngine:
    def __init__(self, access_token: str):
        self.access_token = access_token
        self.api_base = "https://api.figma.com/v1"
# ...
    def get_file_structure(self, file_key: str) -> dict:
        """获取文件完整结构(PRO 专属)"""
Confidence
91% confidence
Finding
The skill transmits data to the Figma API, which is expected for its functionality, but it still represents external transmission of potentially sensitive design content and access tokens. In this context, the risk is real because enterprise design files may include confidential product information, though the transmission is not inherently malicious.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.