CVE-2026-105697: Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio tra
Summary
Langflow, a tool for building AI-powered agents and workflows, has a critical vulnerability where users can execute arbitrary operating system commands by adding malicious MCP servers (server configurations that connect to external tools). An attacker can reach this feature through the settings panel or by building a flow with MCP Tools, and the malicious command runs immediately when Langflow tries to connect to the server, with the highest privileges if auto-login is enabled.
Solution / Mitigation
Update to Langflow 1.10.3, langflow-base 0.10.3, or lfx 1.10.3. Additionally, disable the LANGFLOW_AUTO_LOGIN setting, which is documented as development-only, to prevent unauthenticated access on exposed instances.
Vulnerability Details
9.9(critical)
EPSS: 0.0%
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
network
low
low
none
October 5, 2026
Classification
Taxonomy References
Affected Vendors
Related Issues
CVE-2026-63086: text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compat
CVE-2026-34371: LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the e
Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-105697
First tracked: October 5, 2026 at 08:07 PM
Classified by LLM (prompt v3) · confidence: 95%