CVE-2026-105697— Langflow：MCP stdio 服务器配置中通过任意命令导致远程代码执行漏洞
一分钟漏洞结论
影响对象
langflow-ai langflow
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。
Langflow 是一款用于构建和部署 AI 驱动的智能体（agents）与工作流的工具。在 Langflow 1.10.3 版本之前，MCP 的 stdio 传输机制会执行用户在任何 MCP 服务器配置中提供的任意命令/参数，且未设置任何白名单限制。此外，在 1.10.3 之前，这些命令还被包裹在 中执行。 任何能够访问 MCP 服务器设置界面（路径为：“Settings → MCP Servers → Add MCP Server”，或通过 HTTP POST/PATCH 请求 ）的用户，或者能够使用 MCP
获取后续新漏洞提醒
登录后订阅
一、 漏洞 CVE-2026-105697 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
Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration
来源: CVE Program / CVE List V5
Vulnerability Description
Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...". Any user able to reach the MCP server settings ("Settings → MCP Servers → Add MCP Server", POST/PATCH /api/v2/mcp/servers/{server_name}) or to build a flow with the MCP Tools component could add a "server" whose command is an arbitrary OS command (touch, rm -rf, a reverse shell, ...). The command runs on the Langflow host as the Langflow process user as soon as Langflow tries to connect to the server (listing servers, loading tools, running the flow) — even when the UI then reports that the stdio server failed to start. With the default LANGFLOW_AUTO_LOGIN=true, GET /api/v1/auto_login hands out a token without credentials, so on an exposed instance running the default configuration this is reachable without an account. AUTO_LOGIN is documented as a development-only setting; with it disabled, any authenticated (non-admin) user can exploit it. This issue is fixed in Langflow 1.10.3, langflow-base 0.10.3, and lfx 1.10.3.
来源: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
来源: CVE Program / CVE List V5
Vulnerability Type
OS命令中使用的特殊元素转义处理不恰当(OS命令注入)
来源: CVE Program / CVE List V5
受影响产品
| 厂商 | 产品 | 影响版本 | CPE | 订阅 |
|---|---|---|---|---|
| langflow-ai | langflow | >= 1.1.2, < 1.10.3 | - |
|
| langflow-ai | langflow-base | >= 0.1.2, < 0.10.3 | - |
|
| langflow-ai | lfx | < 1.10.3 | - |
|
二、漏洞 CVE-2026-105697 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-2026-105697 的情报信息
请登录查看更多情报信息。
CVE-2026-105697 其他参考 (6)
-
https://github.com/langflow-ai/langflow/pull/14036 x_refsource_MISC
-
https://github.com/langflow-ai/langflow/pull/12290 x_refsource_MISC
-
https://github.com/langflow-ai/langflow/releases/tag/v1.10.3 x_refsource_MISC
-
https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45 x_refsource_CONFIRM
同批安全公告 · langflow-ai · 2026-10-05 · 共 5 条
| CVE-2026-105740 | 9.9 CRITICAL | Langflow 远程代码执行漏洞 |
| CVE-2026-105699 | 7.1 HIGH | Langflow 跨项目文件泄露漏洞 |
| CVE-2026-105741 | 7.1 HIGH | Langflow `X-Forwarded-For`绕过远程配置写入漏洞 |
| CVE-2026-105698 | 5.4 MEDIUM | Langflow 旧版 API 端点跨用户流程访问与顶点执行漏洞 |
IV. Related Vulnerabilities
V. Comments for CVE-2026-105697
暂无评论