Back to skill

Security audit

Spindle Box

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward CAD-generation workflow, but users should know it sends design parameters to jixietools.com and creates a guest-accessible result link.

Before installing, confirm that sending spindle-box parameters to jixietools.com is acceptable for your designs, treat filename and guest_code values as sensitive workflow links, and verify the category ID mismatch with the publisher because it could fetch the wrong product set.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (10)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

Step 1: 列出主轴箱产品

  1. 用 curl 获取主轴箱列表:
    bash
    curl -s "https://jixietools.com/api/v1/products?category_id=8" | python3 -m json.tool
    

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

Step 1: 列出主轴箱产品

  1. 用 curl 获取主轴箱列表:
    bash
    curl -s "https://jixietools.com/api/v1/products?category_id=8" | python3 -m json.tool
    

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

用户选择后,获取该产品的参数定义:

bash
curl -s "https://jixietools.com/api/v1/products/PRODUCT_ID/start" | python3 -m json.tool

返回结构:

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 147)May include surrounding context.

  1. 收集要修改的参数名和新值
  2. 构建增量请求:只包含变化的参数 + filename:
    bash
    curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"修改的参数名": "新值"}, "filename": "之前保存的filename"}'
    

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough that ordinary mentions of '主轴箱' or 'spindle-box' may invoke the skill even when the user did not intend to start an external CAD-generation and work-order process. Because the skill later sends data to a third-party service and creates guest-accessible production sheets, accidental invocation can lead to unintended external actions and data transmission.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill declares a spindle-box category ID of 40 but the actual product-list request uses category_id=8, creating an inconsistency that can direct users to the wrong product set. In a CAD/work-order workflow, this can cause unintended product selection and downstream creation of incorrect production sheets or disclosure of unrelated product data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

The skill instructs the agent to send user-supplied or workflow-derived parameters to an external API for dropdown precomputation. Even though the payload may appear limited, it still transmits user interaction data to a third-party service without an explicit privacy boundary, which is risky in an engineering workflow where parameters may reflect proprietary design requirements.

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

  • 有 options_source 的参数(下拉选项类型): 先进行一次预计算获取 dropdown 选项:
    bash
    curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"有选项的参数名": ""}}'
    

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The incremental update request sends modified parameters plus a persistent filename token to an external service, linking multiple edits to the same backend workbook state. This increases sensitivity because the filename acts as a workflow handle; if leaked or misused, it may enable unauthorized continuation, manipulation, or correlation of a user's design session.

Content

Scanner excerpt · SKILL.md (reported line 147)May include surrounding context.

  1. 收集要修改的参数名和新值
  2. 构建增量请求:只包含变化的参数 + filename:
    bash
    curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"修改的参数名": "新值"}, "filename": "之前保存的filename"}'
    

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill creates and monitors a guest production sheet via a public link without a prominent pre-action warning or explicit user consent. This is dangerous because filenames, guest codes, and generated drawing outputs become accessible through shareable URLs, which can expose potentially sensitive engineering or procurement information to unintended parties.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction "用中文与用户对话" mandates a specific language for all interactions. This is a natural-language policy concern because it does not offer the user a language choice or indicate that Chinese is optional or contextually required.

Content

No source excerpt is available for this finding.