CVE-2026-59225 Open WebUI: Arena task endpoints can bypass underlying model access controls

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.8.12 before 0.10.0, an authenticated non-admin user with read access to an arena wrapper model can reach a restricted underlying model through task endpoints such as /api/v1/tasks/moa/completions. The...

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...

CVE-2026-44563 Open WebUI: Ollama Model Access Control Bypass via /api/generate, /api/embed, /api/embeddings, and /api/show

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, the /api/generate, /api/embed, /api/embeddings, and /api/show endpoints accept any model name from the user and forward the request to the Ollama backend without checking whether the...

CVE-2026-44563

Open WebUI/Open WebUI’s Ollama integration vulnerability (CVE-2026-44563) affects the /api/generate, /api/embed, /api/embeddings, and /api/show endpoints. These endpoints forward a user-supplied model name to the Ollama backend without enforcing AccessGrants.has_access(), effectively bypassing mo...