UTC
Medium

Chat Hub: chat-only users can register tool types the product already tries to sandbox

GHSA-43v8-hjhm-chjp · published 2026-10-14

Severity
Medium
CVSS score
5.3
Chance of exploitation (EPSS)
No CVE
Fixed in
2.44.1
What it is

Chat Hub blocked only a few tool types for users with the chat user role. A chat user cannot create or edit workflows, but could still add Chat Hub tools that run code in the task runner sandbox, read and write files in the directories that n8n allows, or use the workflows, Data Tables and agents of the instance, and then run these tools through a chat. A chat user could therefore act beyond the limits of their role.

What to do

Upgrade n8n to 2.44.1 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

The issue has been fixed in n8n versions 1.123.85, 2.43.5, and 2.44.1. Users should upgrade to one of these versions or later to remediate the vulnerability.

If you cannot upgrade yet

If upgrading is not immediately possible, administrators should consider the following temporary mitigations: Restrict n8n instance access to fully trusted users only. Do not assign the global:chatUser role to any user who is not fully trusted until the instance is patched. Disable Chat Hub if it is not required. Use the NODES_EXCLUDE environment variable to remove high-risk node types from the instance if they are not needed. Enable N8N_SSRF_PROTECTION_ENABLED=true to reduce the impact of outbound request abuse. These workarounds do not fully remediate the risk and should only be used as short-term mitigation measures.

Affected
PackageRegistryAffectedFixed in
n8nnpm< 1.123.851.123.85
n8nnpm< 2.43.52.43.5
n8nnpm< 2.44.12.44.1

The impact, patch and workaround text comes from the advisory, shortened (published by n8n). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].