← AI agent vulnerabilities

CVE-2026-105740

Langflow

9.9
Severity
Critical
Published
October 5, 2026
Last modified
October 6, 2026

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution (RCE) on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exec {command}" with zero validation, no allowlisting, and no sandboxing. The command executes immediately when the server list is fetched. Additionally, the env field allows arbitrary environment variable injection (e.g., LD_PRELOAD, PATH override). This vulnerability is fixed in 1.9.0.

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

Weakness

References

CVE-2026-105740 on NVD

Listed in

CriticalMCP serversCommand injection

More Langflow CVEs

Oct 5
CVE-2026-1057417.1

An IP spoofing vulnerability in the Model Context Protocol (MCP) configuration installation endpoint (POST /api/v1/mcp/project/{project_id}/install) allowed authenticated remote attackers to bypass the…

Oct 5
CVE-2026-1056979.9

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} ...".