CVE-2026-33696

n8n is an open source workflow automation platform. Prior to versions 2.14.1, 2.13.3, and 1.123.27, an authenticated user with permission to create or modify workflows could exploit a prototype pollution vulnerability in the XML and the GSuiteAdmin nodes. By supplying a crafted parameters as part of node configuration, an attacker could write attacker-controlled values onto `Object.prototype`. An attacker could use this prototype pollution to achieve remote code execution on the n8n instance. The issue has been fixed in n8n versions 2.14.1, 2.13.3, and 1.123.27. Users should upgrade to one of these versions or later to remediate the vulnerability. If upgrading is not immediately possible, administrators should consider the following temporary mitigations: Limit workflow creation and editing permissions to fully trusted users only, and/or disable the XML node by adding `n8n-nodes-base.xml` to the `NODES_EXCLUDE` environment variable. These workarounds do not fully remediate the risk and should only be used as short-term mitigation measures.

An adversary obtains a low-privilege n8n account via credential stuffing, phishing, or insider threat. They create or modify a workflow containing an XML node with crafted parameters that write attacker-controlled values onto Object.prototype. When the workflow executes, the polluted prototype causes Node.js to execute attacker-supplied code with n8n process privileges. In an AI agent context, this grants full control of the orchestrator — the attacker silently modifies agent system prompts, redirects tool calls to attacker-controlled endpoints, and exfiltrates the credentials used to authenticate against every LLM API, vector database, and connected service in the automation pipeline.