UTC
High

Open WebUI's chat completion API allows tool restrictions to be bypassed

CVE-2026-45350 · GHSA-4pcg-253r-rf9w · published 2026-05-14 · updated 2026-05-19

Severity
High
CVSS score
7.1
Chance of exploitation (EPSS)
0.27%
Fixed in
0.8.6
  • Exploitation Public proof of concept
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

This issue may lead to restricted tools being invoked by users via the chat completion API

What to do

Upgrade open-webui to 0.8.6 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Fixed across two releases Local Tool records (toolids: [" "] referencing a stored Tool): fixed in commit 9b06fdc8f, first released in v0.7.0. gettools() in backend/openwebui/utils/tools.py (line 166) now resolves the caller's group memberships and rejects each requested toolid whose owner isn't the caller and for which no grant exists. Admins continue to bypass when BYPASSADMINACCESSCONTROL is enabled (its documented UI/posture purpose). The MCP-resolution loop in backend/open_webui/utils/middleware.py (line 2670) now calls and skips the server with a warning if the user has no grant — the server's stored credentials are never used on behalf of an unauthorized caller.

Affected
PackageRegistryAffectedFixed in
open-webuiPyPI<= 0.8.50.8.6

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].