PT-2026-39273 · Unknown · Open-Webui

CVE-2026-44556

·

Published

2026-05-08

·

Updated

2026-07-13

CVSS v3.1

7.1

High

VectorAV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:H
Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.9.0
Description The '/responses' endpoint in the OpenAI router allows any authenticated user to forward requests to upstream LLM providers without enforcing per-model access control. While the generate chat completion() function validates model ownership, group membership, and AccessGrants, the '/responses' proxy only verifies the user session via get verified user(). Consequently, an authenticated user can interact with any configured model by sending a POST request to '/api/openai/responses' using an arbitrary model ID. This can lead to Model Denial of Service by exhausting API budgets or rate limits through resource-intensive models, and Model Theft via unauthorized interaction with fine-tuned or self-hosted models, effectively bypassing administrative access policies.
Recommendations Update to version 0.9.0.

Exploit

Fix

Missing Authorization

Improper Access Control

Found an issue in the description? Have something to add? Feel free to write us 👾

Weakness Enumeration

Related Identifiers

CVE-2026-44556
GHSA-HP5M-24VP-VQ2Q
PYSEC-2026-2734

Affected Products

Open-Webui