CVE-2026-44556
HighSummary
In versions prior to 0.9.0, the /responses endpoint in the OpenAI router accepts any authenticated user and forwards requests to LLM providers without enforcing per-model access control. This allows any authenticated user to interact with any model configured on the instance.
Risk Assessment
The organization may be exposed to unauthorized access to AI models, potentially leading to data leaks or misuse of resources. Users may gain access to models they should not have access to.
Recommendation
It is recommended to upgrade to version 0.9.0 or later to fix this vulnerability. Additionally, conduct an audit of user permissions and access control to models.
Original NVD description (English source)
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.