Back to skill

Security audit

Spray Dryer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow for generating spray-dryer CAD drawings through a specific external API, with no local code, credential access, or hidden persistence found.

Install only if you are comfortable sending spray-dryer design inputs and generated workflow identifiers to jixietools.com without login. Avoid using it for confidential or proprietary engineering designs unless you trust that service, and verify the category ID mismatch before relying on product selections.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

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: 列出喷雾干燥器产品

  1. 用 curl 获取喷雾干燥器列表:
    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: 列出喷雾干燥器产品

  1. 用 curl 获取喷雾干燥器列表:
    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"}'
    

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

L014 明确写明“喷雾干燥器分类 ID: 38”,但 L031 的实际示例请求却使用 category_id=8。这是文档对实现行为的直接矛盾,会导致技能按错误分类拉取产品,与其宣称的喷雾干燥器流程不一致。

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
79% confidence
Finding

The skill instructs the agent to transmit user-supplied or workflow-derived data to an external third-party API to precompute dropdown options. Even though the payload looks limited, this is still external data transmission without any mention of user consent, data minimization, or domain allowlisting, so it can expose sensitive design parameters to an untrusted service.

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
87% confidence
Finding

The incremental calculation step repeatedly sends modified parameters plus a persistent filename token to an external API. Because the filename acts as a workflow handle and the parameters may contain proprietary engineering data, this creates a meaningful risk of unintended disclosure or cross-session data exposure if the external service is not trusted or access-controlled.

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"}'
    

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L213 instructs the skill to always use Chinese when interacting with the user. This is a natural-language locale policy constraint applied universally, and the file does not indicate that the user can choose another language or opt in to Chinese-only behavior.

Content

No source excerpt is available for this finding.