CVE-2026-70487: Open WebUI: IDOR leaks other users' RAG file content

## Summary Open WebUI lets a client define a model inline on a chat request instead of selecting a saved workspace model. The knowledge attached to such an inline model was used as-is, without checking that the caller can read what it points at. Any authenticated user who knows another user's file id could therefore have the builtin knowledge tools return that file's indexed content back to them. ## Preconditions Authenticated user of any role, no admin rights needed. The request must carry a session id and use native function calling, which is the default (only `function_calling: legacy` opts out), and the model's `builtin_tools` capability must not be disabled (default enabled). The attacker must already know the target file's id; ids are UUIDs and are not enumerable through this path. No admin setting needs to be turned on: enabling Direct Connections is not required for the backend to accept an inline model. Knowledge bases attached this way were never affected, their own access grants were enforced on every path. ## Impact An authenticated user could read the indexed chunks of another user's or group's file, a cross-user confidentiality loss limited to files whose ids the attacker already holds. It is read-only: nothing is modified or deleted, knowledge-base permissions are unaffected, and saved workspace models were already validated at creation time. ## Fix Fixed in 0.11.0 by commit 305880f2e. An inline model's attached knowledge is filtered against the caller's real read access before it is used, dropping any file, knowledge base or note the caller cannot read. Upgrading fully resolves it, no configuration change is required. ## Root cause Affected component: the chat completion, chat completed and chat action endpoints, which accept an inline model definition, and the builtin knowledge tools that consume the model's attached knowledge. Affected setups: all builds from 0.8.8 through 0.10.2. Saved workspace models have their attached file references validated against the author when the model is created, updated or imported, so a stored model can only carry files its creator can read. An inline model never passes through that path, yet everything downstream treated its attached knowledge with the same trust, including a helper that grants read access to a file purely because the running model claims it as attached knowledge. The missing control was an access check at the point where client-supplied model metadata enters the request. ## Credits Reported by @whyiug.

An organization runs a shared Open WebUI instance for its analyst team, each with individual accounts but common visibility into some file ids (e.g., surfaced in a Slack link, a support ticket, or a previous group chat session). A curious or malicious analyst who has seen a colleague's file id — perhaps a compensation spreadsheet or an incident report uploaded to their private knowledge — crafts a raw API request to the chat completion endpoint with an inline model definition pointing its attached knowledge at that file UUID, using the default native function-calling mode. The built-in knowledge tool retrieves and returns the indexed chunks of that file directly in the chat response, without ever checking that the requester has read access, silently exfiltrating the colleague's data with no admin involvement or audit trail distinct from a normal chat query.