Auth bypass in Open-Webui
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.1 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:H.
EPSS exploit prediction
EPSS: 0.004 (28.5th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 28th percentile — 28.5% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.004 · change: +0.001
Affected products
- Open-Webui — versions < 0.9.0
- Openwebui Open Webui
Weakness classification (CWE)
References
- github.com/open-webui/open-webui/security/advisories/GHSA-hp5m-24vp-vq2q (Vendor Advisory)
Frequently asked questions
- What is CVE-2026-44556?
- CVE-2026-44556 is a high-severity vulnerability in Open-Webui, classified under Improper Access Control. CVSS score: 7.1/10. Published 2026-05-15.
- How severe is CVE-2026-44556?
- High severity. CVSS v3 base score is 7.1 out of 10.