ClawHub
Back to skill

Security audit

Gb Arch Cad Gen

Security checks for vulnerabilities and agentic risk

Overview

This CAD skill does not appear to steal data, but it overstates building-code compliance and can still generate drawings after detecting violations.

Install only if you treat the output as draft/reference material and independently verify building-code compliance with a qualified professional. Do not rely on it for permitting, construction, or safety decisions unless mandatory-rule validation is made blocking and the dependency/version handling is tightened.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The skill markets itself as strictly complying with mandatory Chinese building standards, but when validation fails it only logs warnings and continues generating output. In a building-design context, this can mislead users into relying on non-compliant drawings for downstream design, review, or construction decisions, creating real safety, legal, and compliance risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill declares both file-writing and command-execution capabilities, including running Node.js scripts and writing output files, but does not present a clear user-facing warning or consent boundary around those side effects. In an agent environment, this increases the risk of unintended local file creation, path misuse, or unsafe command construction if later implementation interpolates user input into shell commands.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"draw": "node scripts/main.js"
  },
  "dependencies": {
    "makerjs": "^0.18.1"
  },
  "keywords": ["openclaw", "skill", "cad", "architecture", "china-standard"],
  "license": "MIT"
Confidence
96% confidence
Finding
The dependency uses a caret range (^0.18.1), allowing installation of future 0.x releases that may change behavior or introduce malicious or vulnerable code through the supply chain. In a build or runtime environment, this weakens reproducibility and can silently pull different package contents over time, increasing risk.

Known Vulnerable Dependency: makerjs==0.18.1 — 1 advisory(ies): CVE-2026-24888 (Maker.js has Unsafe Property Copying in makerjs.extendObject)

Low
Category
Supply Chain
Confidence
98% confidence
Finding
The manifest references makerjs 0.18.1, which is reported as affected by unsafe property copying in extendObject. If untrusted input can influence objects passed into the vulnerable code path, this may enable prototype pollution or unintended property injection, potentially affecting application logic or downstream consumers of generated drawing data.

Static analysis

No suspicious patterns detected.