High severity8.1NVD Advisory· Published Mar 26, 2026· Updated Apr 30, 2026
CVE-2025-12805
CVE-2025-12805
Description
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.
Affected products
1- cpe:2.3:a:redhat:openshift_ai:2.25:*:*:*:*:*:*:*
Patches
0No patches discovered yet.
Vulnerability mechanics
AI mechanics synthesis has not run for this CVE yet.
References
4- bugzilla.redhat.com/show_bug.cginvdExploitIssue TrackingVendor Advisory
- access.redhat.com/errata/RHSA-2026:2106nvdVendor Advisory
- access.redhat.com/errata/RHSA-2026:2695nvdVendor Advisory
- access.redhat.com/security/cve/CVE-2025-12805nvdVendor Advisory
News mentions
0No linked articles in our index yet.