CVE-2026-86082

Received Received - Intake

OpenAI Chat Model Credential Exposure in n8n

Publication date: 2026-09-08

Last updated on: 2026-09-08

Assigner: GitHub, Inc.

Description

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.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-09-08

Last Modified

2026-09-08

Generated

2026-09-09

AI Q&A

2026-09-09

EPSS Evaluated

N/A

NVD

CVE-2026-86082

Affected Vendors & Products

Vendor	Product	Version / Range
n8n	n8n	to 1.123.76 (inc)
n8n	n8n	to 2.37.7 (inc)
n8n	n8n	to 2.38.2 (inc)

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-918	The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

Attack-Flow Graph

Executive Summary

The vulnerability in n8n versions before 1.123.76, 2.37.7, and 2.38.2 allows a workflow editor to bypass credential domain restrictions in the OpenAI Chat Model node. By setting options.baseURL to an arbitrary host, the model-search dropdown could send the OpenAI API credential to an unauthorized host. This occurs because the affected code in loadModels.ts did not enforce allowed-domain checks for this specific path.

Impact Analysis

An attacker with workflow editing access could exfiltrate OpenAI API credentials to an external host, potentially leading to unauthorized API usage, data leakage, or further attacks. This could result in financial costs from API overuse or exposure of sensitive data processed through the workflow.

Compliance Impact

This vulnerability could lead to unauthorized data exposure, violating GDPR's data protection principles or HIPAA's security requirements for protected health information. Organizations using n8n may face compliance violations if credentials or data are mishandled due to this flaw.

Mitigation Strategies

Update n8n to version 1.123.76, 2.37.7, or 2.38.2 or later to address the vulnerability in the OpenAI Chat Model node.

Hi! I’m here to help you understand CVE-2026-86082. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70