CVE-2026-44556
Description
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
open-webuiPyPI | < 0.9.0 | 0.9.0 |
Affected products
2<= 0.8.12+ 1 more
- (no CPE)range: <= 0.8.12
- cpe:2.3:a:openwebui:open_webui:*:*:*:*:*:*:*:*range: <0.9.0
Patches
Vulnerability mechanics
References
4- github.com/advisories/GHSA-hp5m-24vp-vq2qghsaADVISORY
- github.com/open-webui/open-webui/security/advisories/GHSA-hp5m-24vp-vq2qnvdVendor AdvisoryWEB
- nvd.nist.gov/vuln/detail/CVE-2026-44556ghsaADVISORY
- github.com/open-webui/open-webui/pull/23481ghsaWEB
News mentions
0No linked articles in our index yet.