CVE-2026-45351 Open WebUI: Exposure of System Prompt to Regular User [Non-Admin]

Medium 6.5 Published Updated

Regular users can view admin-configured system prompts for AI models, compromising confidentiality.

Exploited in the wild
Not known
Login needed
Any signed-in user
Attackable
Over the internet
Victim action needed
Not needed
Fix
Available

What is CVE-2026-45351?

CVE-2026-45351 is a medium-severity vulnerability in Openwebui Open Webui, published on 15 May 2026. Any signed-in user can exploit it over the network, with no action from the victim.

Official description

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.9, when a regular user [non-admin] logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available models set by admin on models pages in workspace affecting the confidentiality of application. This vulnerability is fixed in 0.8.9.

Weakness: CWE-200

Which versions are affected by CVE-2026-45351?

3 open source packages ship an affected version, including open-webui. It affects 1 product.

PackageAffectedFixed in
open-webui PyPIAll versions0.8.9
open-webui PyPIAll versions0.8.9
open-webui PyPIAll versions0.8.9

Products include Openwebui Open Webui.

How do I fix CVE-2026-45351?

Upgrade open-webui to 0.8.9 or later.

Is CVE-2026-45351 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-45351 exists.

All Openwebui Open Webui vulnerabilities

Sources

Also known as GHSA-jh9g-8jqw-m2qx, PYSEC-2026-2741.

Is CVE-2026-45351 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free