---
id: CVE-2026-86082
title: n8n is an open source workflow automation platform
summary: >-
  n8n is an open source workflow automation platform. Prior to 1.123.76, 2.37.7,
  and 2.38.2, the OpenAI Chat Model node enforced credential allowed-domain
  restrictions for normal calls but not for the model-search dropdown. A
  workflow edit…
severity: medium
cvss: 6.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N'
cwe:
  - CWE-918
vendor: n8n
product: n8n
affected:
  - n8n < 1.123.76
  - 'n8n >= 2.0.0, < 2.37.7'
  - 'n8n >= 2.38.0, < 2.38.2'
patched:
  - n8n 2.38.2
published: '2026-09-08'
updated: '2026-09-14'
sourceUpdated: '2026-09-14T13:18:57.487'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-86082'
references:
  - url: 'https://github.com/n8n-io/n8n/releases/tag/n8n@1.123.76'
    label: security-advisories@github.com
  - url: 'https://github.com/n8n-io/n8n/releases/tag/n8n@2.37.7'
    label: security-advisories@github.com
  - url: 'https://github.com/n8n-io/n8n/releases/tag/n8n@2.38.2'
    label: security-advisories@github.com
  - url: 'https://github.com/n8n-io/n8n/security/advisories/GHSA-34ff-336r-5q23'
    label: security-advisories@github.com
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-86082'
  - url: 'https://github.com/advisories/GHSA-34ff-336r-5q23'
tags:
  - nvd
  - cve.org
  - ghsa
  - npm
ssvc:
  exploitation: none
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-09-14T12:03:11.876834Z'
scores:
  nvd: 6.5
  cna: 7.1
epss: 0.00415
epssPercentile: 0.33144
aliases:
  - GHSA-34ff-336r-5q23
ecosystem: npm
ingestedAt: '2026-09-08T22:12:31.038Z'
---

## Overview

n8n is an open source workflow automation platform. Prior to 1.123.76, 2.37.7, and 2.38.2, the OpenAI Chat Model node enforced credential allowed-domain restrictions for normal calls but not for the model-search dropdown. A workflow editor could set options.baseURL to an arbitrary host and make the searchModels path send the openAiApi credential there. The affected implementation is packages/@n8n/nodes-langchain/nodes/llms/LMChatOpenAi/methods/loadModels.ts, which omitted assertOpenAiCredentialAllowsUrl. This issue is fixed in versions 1.123.76, 2.37.7 and 2.38.2.

## Affected

- `n8n < 1.123.76`
- `n8n >= 2.0.0, < 2.37.7`
- `n8n >= 2.38.0, < 2.38.2`

## Remediation

Upgrade past the affected range:

- `n8n 2.38.2`

## Package advisory (CVE-2026-86082)

Affected packages:

- `n8n < 1.123.76`
- `n8n >= 2.38.0, < 2.38.2`
- `n8n >= 2.0.0, < 2.37.7`

Patched in:

- `n8n 1.123.76`
- `n8n 2.38.2`
- `n8n 2.37.7`

Source: https://github.com/advisories/GHSA-34ff-336r-5q23