Skip to content
Fencer Vulns
critical 9.9

CVE-2026-105697 json

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

published 2026-10-05 34 d ago modified 2026-10-15 24 d ago also GHSA-w794-rj3p-xv45 , PYSEC-2026-4237 , PYSEC-2026-4239 , PYSEC-2026-4241 , EUVD-2026-92788

cvss
9.9
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.9%
EPSS 0.9% chance of exploitation in 30 days, percentile 61%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi langflow 1.10.3
  • pypi langflow-base 0.10.3
  • pypi lfx 1.10.3

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
33 d ago

Exploit prediction

0.95% chance of exploitation in the next 30 days, higher than 61% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 9.9 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
OSV 3.1 9.9 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
GitHub 3.1 9.9 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi langflow
>=1.1.2, <1.10.3
1.10.3
pypi langflow-base
>=0.1.2, <0.10.3
0.10.3
pypi lfx
<1.10.3
1.10.3

Affected products

  • langflow-ai langflow
  • langflow-ai langflow-base
  • langflow-ai lfx

Classification

Weakness
  • CWE-78 Improper Neutralization of Special Elements used in an OS Command

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.