ClawHub
Back to skill

Security audit

Figma Implement Design

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Figma-to-code workflow that uses Figma MCP access in ways that fit its stated purpose.

Install this only if you are comfortable connecting Codex to Figma MCP and authorizing Figma access. When using the desktop selection flow, verify that the open Figma file and selected node are the design you intend to share before asking the agent to fetch context or screenshots.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Context Leakage

High
Category
Data Exfiltration
Confidence
96% confidence
Finding

The skill instructs the agent to use the currently selected node from the Figma desktop app when no URL is provided, which can pull design context from a local application state the user did not explicitly identify in the prompt. That creates a real context-leakage risk: an attacker can socially engineer the agent into exfiltrating screenshots, metadata, or assets from whichever confidential design happens to be selected.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

md
When using the `figma-desktop` MCP and the user has NOT provided a URL, the tools automatically use the currently selected node from the open Figma file in the desktop app.

**Note:** Selection-based prompting only works with the `figma-desktop` MCP server. The remote server requires a link to a frame or layer to extract context. The user must have the Figma desktop app open with a node selected.

### Step 2: Fetch Design Context

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill metadata describes a broad purpose—turning Figma designs into production-ready code—without embedding strong activation constraints in the agent-facing interface. This can cause the skill to trigger in loosely related contexts and grant access to an external MCP service when the user did not clearly request Figma-based implementation, increasing the chance of unintended data exposure or overbroad tool use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.