Vulnerability · Published May 15, 2026 · Assigned by GitHub_M

CVE-2026-45387Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)

Medium 4.3

In plain English

A medium-severity information exposure in open-webui from open-webui. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 13% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)4.3Medium

Exploit odds (30 days)0.2%top 87.4% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, when setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model's system prompt. However users may consider their system prompt confidential, so this is considered a security issue. This vulnerability is fixed in 0.9.5.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	open-webui	0.9.5	GHSA-h2cw-7qw9-56xr
PyPI	open-webui	0.9.5	PYSEC-2026-2728

Affected products (as reported)

Vendor	Product	Versions
open-webui	open-webui	< 0.9.5

Weakness: CWE-200 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N

References

https://github.com/open-webui/open-webui/security/advisories/GHSA-h2cw-7qw9-56xr x_refsource_CONFIRM