CVE-2026-105697 · GHSA-w794-rj3p-xv45

Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Risk score: 72/100
CVSS: 9.9 v3.1
Exploit chance (30 days): 0.5%
Published: 5 Oct 2026

Open in the live forecast Today's forecast

What to know

What it is: 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…
Affected: langflow (pip) >= 1.1.2, < 1.10.3; langflow-base (pip) >= 0.1.2, < 0.10.3; lfx (pip) < 1.10.3
Fix: Upgrade langflow to 1.10.3; langflow-base to 0.10.3; lfx to 1.10.3 or later.
Exploitation: No known exploitation

Story map

Story map: the flaws, the fix, how it unfolded and what it connects to. Boxes link to the record or article.

At a glance

langflow: Red, act today. Langflow's built-in Python interpreter components — PythonREPLComponent (Python Interpreter) and the legacy PythonREPLToolComponent (Python REPL Tool) — executed arbitrary user- or model-supplied Python code inside flows without effective sandboxing. Because the code ran in-process with the privileges of the Langflow …

The flaws

CVE-2026-105697: Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration (CVSS 9.9 · EPSS 0%)
CVE-2026-10561: Langflow: PythonREPLComponent executes unsandboxed Python code, enabling authenticated RCE and privilege escalation (CVSS 9.9 · EPSS 1%)
CVE-2026-51886: Langflow: Title Authenticated Remote Code Execution in validate_code via Malicious Decorators Description (CVSS 9.8 · EPSS 0%)
CVE-2026-7873: Langflow: Code Injection Vulnerability in Code Validation Endpoint (CVSS 9.9)

The fix

Upgrade langflow: 1.10.3 · 1.10.1 or later on your release line

Who is exposed: langflow (pip) < 1.10.1

Where it stands

No known exploitation

Connects to

Same weakness: OS command injection (CWE-78). 308 other warnings in 30 days

Why it is Amber

CVSS 9.9 critical
On your watchlist: PyPI

Affected packages

Package	Ecosystem	Vulnerable	Fixed in
langflow	pip	>= 1.1.2, < 1.10.3	1.10.3
langflow-base	pip	>= 0.1.2, < 0.10.3	0.10.3
lfx	pip	< 1.10.3	1.10.3

References

Original 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.

Last activity 5 Oct 2026. Patch Forecast updates every hour.