CVE catalog

CVE-2025-12805

A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, b

[CVE catalog]

Severity
High · CVSS 8.1CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Published
Source
[NVD] · [CVE record]
EPSS
0.39% · Oct 25, 2026

A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data. llama-stack-k8s-operator: Llama Stack service exposed across namespaces due to missing NetworkPolicy This is an IMPORTANT flaw in Red Hat OpenShift AI (RHOAI). The `llama-stack-operator` fails to implement a `NetworkPolicy`, enabling unauthorized access to Llama Stack services across different namespaces. This allows users to potentially view or manipulate sensitive data belonging to other users within the same RHOAI instance. The CVSS score(s) listed for this vulnerability do not reflect the associated product's status, and are included for informational purposes to better understand the severity of this vulnerability.

Vulnerable and fixed packages

Distribution-reported package versions and fixes. These do not depend on matching against the OpenFactory package catalog.

DistributionPackageReleaseVersionStatus
Cpeopenshift_aiNot reportedNot reportedunknown

Fixed-version evidence

OpenFactory catalog packages

No matching packages in this catalog.

Observed:

References