Gb Arch Cad Gen

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 8:56 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed CAD floor-plan generator that writes local SVG/PDF outputs, with notable quality and dependency cautions but no artifact-backed hidden, destructive, or exfiltrating behavior.

Install only if you are comfortable with a Node-based skill that may install npm packages and write generated CAD files locally. Treat its drawings as conceptual drafts, not construction-ready or legally compliant outputs, and review dependency versions before running in a sensitive environment.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (8)

Tp2

High

• Category: MCP Tool Poisoning
• Confidence: 85% confidence

Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The trigger set is broad and overlaps with ordinary architecture and CAD requests, which can cause the skill to activate in situations where the user did not explicitly intend to invoke it. In a skill that can write files and execute Node.js via command_exec, overbroad activation increases the chance of unintended tool use, unsafe file generation, or prompt-routing abuse through ambiguous requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The file description and comments explicitly position the skill as a Chinese-standard CAD generator and are written entirely in Chinese, indicating a fixed language/locale context. There is no natural-language indication that users may choose another language/locale or that the restriction is an explicit opt-in; this can violate language/locale choice policy.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill advertises strict compliance with mandatory Chinese building standards, but when validation detects violations it only logs warnings and proceeds to generate output. In an architectural CAD context, this can mislead users into treating non-compliant drawings as standards-conformant, creating real safety, legal, and operational risk if the drawings are used downstream.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The package description states the skill is a "中国规范 CAD 图纸生成器," which indicates a China-specific standards and language context. In this manifest, there is no accompanying explanation that the skill is region-specific by design or that users can opt into this locale, so it may violate the language/locale policy criterion.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low

• Category: Supply Chain
• Confidence: 91% confidence

Finding

The dependency on makerjs is specified with a caret range (^0.18.1), which allows newer compatible releases to be installed without explicit review. This weakens build reproducibility and can expose consumers to accidental introduction of vulnerable or malicious upstream changes, especially in an automated skill execution environment.

Content

Scanner excerpt · package.json/document.md (reported line 10)May include surrounding context.

md

"draw": "node scripts/main.js"
  },
  "dependencies": {
    "makerjs": "^0.18.1"
  },
  "keywords": ["openclaw", "skill", "cad", "architecture", "china-standard"],
  "license": "MIT"

Unverifiable Dependency: makerjs has 1 known advisory(ies) (CVE-2026-24888 (Maker.js has Unsafe Property Copying in makerjs.extendObject)), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low

• Category: Supply Chain
• Confidence: 90% confidence

Finding

The manifest references makerjs without an exact version while there is a known advisory affecting some Maker.js releases (unsafe property copying in extendObject). Because the installed version is not fixed, it is impossible to verify from this manifest alone whether deployments may resolve to an affected version, creating supply-chain and potentially prototype-pollution risk depending on how the library is used.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The comment at L177-L179 describes creating windows according to drafting standards, which semantically implies window entities rather than doors. However, every window path is assigned LAYERS.DOOR, contradicting the documented intent and undermining standards-based layering claims.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.