ClawHub
Back to skill

Security audit

implement-design

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Figma-to-code workflow that uses the Figma MCP server as expected, with only transparency and activation-scope notes.

Install this skill if you want an agent to implement UI from Figma links. Use it with explicit Figma URLs and be aware it will query the connected Figma MCP server and may use localhost asset URLs returned by that server.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description uses broad activation phrases like "generate code" and "implement component," which can match many ordinary development requests and cause the skill to auto-activate in contexts where the user did not explicitly intend Figma-based data retrieval. In this skill, unintended activation is more concerning because the prescribed workflow then encourages fetching external design context and assets from the Figma MCP server, potentially causing unnecessary external access or disclosure of project context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The workflow instructs the agent to fetch design context, screenshots, and assets from the Figma MCP server without explicitly telling the user that their request will trigger external retrieval of design data and localhost-hosted assets. This reduces transparency and informed consent, and in ambiguous cases may surprise users by causing external data access they did not expect.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.