# Open WebUI's Ollama Model Access Control Bypass via /api/generate, /api/embed, /api/embeddings, and /api/show

Advisory record · `GHSA-rcvp-6fgw-c7fh`

- **Identifiers:** `GHSA-rcvp-6fgw-c7fh` · `CVE-2026-44563` · `PYSEC-2026-2754`
- **State:** Confirmed
- **Severity:** CVSS 5.4 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-862](https://cwe.mitre.org/data/definitions/862.html)
- **Tags:** [Broken access control](https://agentprime.io/advisories/tag/access-control.md)
- **Published:** 8 May 2026
- **Updated:** 13 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 8 May 2026, 19:52 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `open-webui` (PyPI): affected `<0.9.0`; fixed in `0.9.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> Open WebUI versions before 0.9.0 do not enforce model access control on four Ollama proxy endpoints (/api/generate, /api/embed, /api/embeddings and /api/show). Any authenticated non-pending user who knows a restricted model's name can call these endpoints to use that model and, through /api/show, read its system prompt, parameters and other configuration. Upgrade to Open WebUI 0.9.0 or later. The source gives no workaround other than upgrading.

Written 6 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 5.4 Medium, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0024, the 14th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 15 May 2026, 20:16 UTC: [Confirmed by NVD](https://nvd.nist.gov/vuln/detail/CVE-2026-44563)
- 31 Oct 2026, 15:03 UTC: First seen by agentprime
- 31 Oct 2026, 15:03 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-rcvp-6fgw-c7fh)

## Sources

- [GitHub Advisory Database: GHSA-rcvp-6fgw-c7fh](https://github.com/advisories/GHSA-rcvp-6fgw-c7fh)
- [OSV: GHSA-rcvp-6fgw-c7fh](https://osv.dev/vulnerability/GHSA-rcvp-6fgw-c7fh)
- <https://github.com/open-webui/open-webui/security/advisories/GHSA-rcvp-6fgw-c7fh>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-44563>
- <https://github.com/open-webui/open-webui>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-rcvp-6fgw-c7fh>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-rcvp-6fgw-c7fh/>. Everything for agents: <https://agentprime.io/llms.txt>.
