Skip to main content
Public proof of conceptFix availableAwaiting NVD analysis

CVE-2026-105697

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

A public proof of concept exists; no exploitation attested.

  • Published2026-10-05
  • Fixed in1.10.3
  • WeaknessCWE-78

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

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.

Timeline

dates in UTC
  1. 2026-10-0521:16CVE publishedNVD
  2. 2026-11-0101:02First public proof of conceptPoC-in-GitHub

Versions per branch

OSV
lfx
BranchAffectedFixed in
1.10< 1.10.31.10.3
langflow
BranchAffectedFixed in
1.x≥ 1.1.2, < 1.10.31.10.3
langflow-base
BranchAffectedFixed in
0.x≥ 0.1.2, < 0.10.30.10.3

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Products declared by the CNA3 products

As GitHub_M, the CNA that assigned this CVE, declared them in the CVE record; versions as written.

  • langflow-ai langflow
    Affected
    • = >= 1.1.2, < 1.10.3no fix stated
  • langflow-ai langflow-base
    Affected
    • = >= 0.1.2, < 0.10.3no fix stated
  • langflow-ai lfx
    Affected
    • = < 1.10.3no fix stated

Source: the CNA record (CVE Program), © The MITRE Corporation,CVE Terms of UseCVE recordupdated 2026-10-09

Fix

  1. Update lfx to 1.10.3

Detection

read 2026-11-01 01:02 UTC
Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof of concept
Metasploit modules
none listed
Metasploit Framework

Sources

Identifiers

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Published
2026-10-05
Last Modified
2026-10-09
NVD status
Awaiting Analysis
GitHub Advisory
GHSA-w794-rj3p-xv45

Frequently asked questions

What is 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.

Is CVE-2026-105697 actively exploited?

Active exploitation of CVE-2026-105697 has not been confirmed. Its EPSS score was 1.5% on 2026-11-18, the estimated probability of exploitation in the next 30 days.

What is the CVSS score for CVE-2026-105697?

CVE-2026-105697 has a CVSS v3 base score of 9.9 (Critical severity), with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H.

Running lfx? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

No credit card required · No monthly cap on website lookups · 250 API requests/month

Sources for this record