← Back to CVE List
Vulnerability Intelligence Report
Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

CVE-2026-105697

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.

Injection No Active Exploit Signals
CVSS Base Score
9.9
CRITICAL
Exploitability:3.2
Impact Score:6.1
EPSS Probability:0.40%
Executive Threat Verdict
Evaluating...
Evaluating Threat Landscape...
Assessing known weaponization, exploitation telemetry, and federal advisories.
Attack Surface
—
Authentication
—
Weaponization
—
SSVC Action
—

Weaknesses (CWE)

CWE-78 ↗CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

Affected Products & Versions

Vendor Product Affected Versions
langflow-ai langflow >= 1.1.2, < 1.10.3 (affected)
langflow-ai langflow-base >= 0.1.2, < 0.10.3 (affected)
langflow-ai lfx < 1.10.3 (affected)

References & Technical Advisories

No reference links found.

Threat Intelligence Signals

EPSS Score
0.396%
Vulnerability Class
Injection

Identity & Timeline

StatusPUBLISHED
Assigning AuthorityGitHub, Inc. · Vendor · USA
Reserved2026-10-05T17:48:58
Published2026-10-05T20:16:58
Last Updated2026-10-09T19:55:07

LINK COPIED TO CLIPBOARD