CVE-2026-105697

CVE Enrichment

CVSS: 9.9 CRITICAL
EPSS: 0.47%
EPSS Percentile: 39.35%
CISA KEV: Not listed

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.

Technical Details

CVSS Version: 3.1
CNA / NVD Source: security-advisories@github.com
Published: 06-Oct-2026 04:16
Last Modified: 10-Oct-2026 03:17
EPSS Date: 2026-10-16
CWE: CWE-78

CVSS Vector


            CVSS:3.1                            AV:N /
                            AC:L /
                            PR:L /
                            UI:N /
                            S:C /
                            C:H /
                            I:H /
                            A:H

References

Last enrichment sync: 17-Oct-2026 08:19
Sources: NVD · FIRST EPSS · CISA KEV
Latest successful provider update; providers refresh independently.

Reported Context (1)

Last month, Langflow also addressed another critical vulnerability (CVE-2026-105697, CVSS score: 9.9) that could also result in operating system command injection through MCP stdio server configuration. Langflow CVE-2026-105740 Draws 1,423 Honeypot Exploit Attempts

CVE (1)

People (1)

MITRE ATT&CK (2)

Products (2)

Countries (15)

Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.