CVE-2026-81096— Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab ToolUniverse 代码注入漏洞
一分钟漏洞结论
影响对象
mims-harvard ToolUniverse
利用判断
尚无明确在野利用证据，仍需结合暴露面评估
建议动作
优先检查厂商安全公告和参考链接中的修复版本；无法立即升级时，限制受影响服务暴露并加强监测。
Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab ToolUniverse是Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab组织的一个汇聚多种机器学习与开发功能的软件工具集。 Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab ToolUni
影响版本矩阵 1
| 厂商 | 产品 | 版本范围 | 状态 |
|---|---|---|---|
| mims-harvard | ToolUniverse | ≤ 1.2.6 |
affected |
获取后续新漏洞提醒
登录后订阅
一、 漏洞 CVE-2026-81096 基础信息
漏洞信息
对漏洞内容有疑问？看看神龙的深度分析是否有帮助！
查看神龙十问 ↗
尽管我们使用了先进的大模型技术，但其输出仍可能包含不准确或过时的信息。神龙努力确保数据的准确性，但请您根据实际情况进行核实和判断。
Vulnerability Title
ToolUniverse through 1.2.6 Unauthenticated Remote Code Execution via python_code_executor Sandbox Escape
来源: CVE Program / CVE List V5
Vulnerability Description
ToolUniverse ran caller-supplied Python inside a sandbox that could be escaped, on a server that required no authentication. The executor behind the python_code_executor tool, in python_executor_tool.py, inspected the submitted source for a denied list of attribute names and calls but left the attribute-lookup builtins available and did not stop a dunder attribute reached through a string lookup or through a module already permitted, so a caller could walk from a literal's class to its base and enumerate subclasses to obtain a reference to the process and subprocess modules. A per-call argument also let the caller widen the import allow-list before the inspection ran. The HTTP and MCP servers in http_api_server.py and smcp_server.py bound to every interface with debugging enabled and no authentication, so any caller able to reach the port executed code as the server process. Version 1.3.0 adds bearer-token authentication, defaults the bind address to loopback, and hardens the attribute checks.
来源: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
来源: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
来源: CVE Program / CVE List V5
Vulnerability Title
Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab ToolUniverse 代码注入漏洞
来源: 中国国家信息安全漏洞库 CNNVD
Vulnerability Description
Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab ToolUniverse是Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab组织的一个汇聚多种机器学习与开发功能的软件工具集。 Artificial Intelligence for Medicine and Science @ Harvard Zitnik Lab ToolUni
来源: 中国国家信息安全漏洞库 CNNVD
CVSS Information
N/A
来源: 中国国家信息安全漏洞库 CNNVD
Vulnerability Type
N/A
来源: 中国国家信息安全漏洞库 CNNVD
受影响产品
| 厂商 | 产品 | 影响版本 | CPE | 订阅 |
|---|---|---|---|---|
| mims-harvard | ToolUniverse | 0 ~ 1.2.6 | - |
|
二、漏洞 CVE-2026-81096 的公开POC
| # | POC 描述 | 源链接 | 神龙链接 |
|---|
AI 生成 POC
高级
未找到公开 POC。
登录以生成 AI POC三、漏洞 CVE-2026-81096 的情报信息
请登录查看更多情报信息。
CVE-2026-81096 补丁与修复 (1)
CVE-2026-81096 厂商安全公告 (2)
-
🔗 Page not found · GitHub · GitHub vendor-advisory
-
CVE-2026-81096 概念验证 (1)
IV. Related Vulnerabilities
V. Comments for CVE-2026-81096
暂无评论