CVE-2026-44556

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, the /responses endpoint in the OpenAI router accepts any authenticated user and forwards requests directly to upstream LLM providers without enforcing per-model access control. While the primary chat completion endpoint (generate_chat_completion) checks model ownership, group membership, and AccessGrants before allowing a request, the /responses proxy only validates that the user has a valid session via get_verified_user. This allows any authenticated user to interact with any model configured on the instance by sending a POST request to /api/openai/responses with an arbitrary model ID. This vulnerability is fixed in 0.9.0.
Configurations

Configuration 1 (hide)

cpe:2.3:a:openwebui:open_webui:*:*:*:*:*:*:*:*

History

19 May 2026, 03:12

Type Values Removed Values Added
First Time Openwebui
Openwebui open Webui
CPE cpe:2.3:a:openwebui:open_webui:*:*:*:*:*:*:*:*
References () https://github.com/open-webui/open-webui/security/advisories/GHSA-hp5m-24vp-vq2q - () https://github.com/open-webui/open-webui/security/advisories/GHSA-hp5m-24vp-vq2q - Vendor Advisory

15 May 2026, 20:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-05-15 20:16

Updated : 2026-05-19 03:12


NVD link : CVE-2026-44556

Mitre link : CVE-2026-44556

CVE.ORG link : CVE-2026-44556


JSON object : View

Products Affected

openwebui

  • open_webui
CWE
CWE-284

Improper Access Control

CWE-862

Missing Authorization