Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration
langflow-ai langflow · langflow-ai langflow-base · langflow-ai lfx
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| langflow PyPI |
|
|
| langflow-base PyPI |
|
|
| lfx PyPI |
langflow-ai langflow · langflow-ai langflow-base · langflow-ai lfx
| Product | Affected | Fixed in |
|---|---|---|
| langflow PyPI |
|
|
| langflow-base PyPI |
|
|
| lfx PyPI |
< 1.10.3
|
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.
From the CVE record · GitHub_M
Langflow’s MCP stdio transport runs commands supplied in MCP server configurations or MCP Tools flows on the host as the Langflow process user when it tries to connect. An authenticated non-admin user can exploit this; on an exposed instance with the default auto-login setting, an attacker can obtain a token without credentials and exploit it without an account.
Check PyPI langflow versions >=1.1.2 and <1.10.3, langflow-base versions >=0.1.2 and <0.10.3, and lfx versions <1.10.3.