CVE-2025-12805Llama-stack-k8s-operator: llama stack service exposed across namespaces due to missing networkpolicy
Beschreibung
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.
Daten: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Wiedergegeben wie in der Quelle, auf Englisch.
Betroffene Produkte und Versionen
| Hersteller | Produkt | Versionen | |
|---|---|---|---|
| openshift ai | 2.25 | — | |
| redhat | openshift ai | 2.25 | |
| Red Hat | Red Hat OpenShift AI 2.25 | all versions | |
| Red Hat | Red Hat OpenShift AI (RHOAI) | — |
Referenzen und Patches
- RHSA-2026:2106 vendor-advisoryVendor Advisory
- RHSA-2026:2695 vendor-advisoryVendor Advisory
- https://access.redhat.com/security/cve/CVE-2025-12805 vdb-entryVendor Advisory
- RHBZ#2413101 issue-trackingExploitIssue TrackingVendor Advisory
CPE-Treffer (NVD) (1)
cpe:2.3:a:redhat:openshift_ai:2.25:*:*:*:*:*:*:*