Critical Langflow flaws enable authentication bypass and RCE

Source: CSO Online · NOV 03, 2026

IBM patched critical vulnerabilities in Langflow, an open-source framework for building AI agents, LLM-powered workflows, and retrieval-augmented generation (RAG) systems. The flaws could allow attackers to bypass authentication, leak API credentials, and execute arbitrary code. Langflow, now owned by IBM, is popular in enterprise environments because it offers a visual experience that doesn’t require coding knowledge to create AI workflows and agents. Vulnerabilities in the framework have been exploited in the wild to steal AI and developer credentials before, most recently in August . This latest round of security patches fix four vulnerabilities , two of which are rated critical with 9.8 CVSS score. One flaw, tracked as CVE-2026-93680, stems from an incomplete remediation of a previous auto-login security issue. Exploiting it could allow attackers to bypass security restrictions and gain access to features that would normally require authentication. Another flaw, CVE-2026-110186, al