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.
References
| Link | Resource |
|---|---|
| https://access.redhat.com/errata/RHSA-2026:2106 | Vendor Advisory |
| https://access.redhat.com/errata/RHSA-2026:2695 | Vendor Advisory |
| https://access.redhat.com/security/cve/CVE-2025-12805 | Vendor Advisory |
| https://bugzilla.redhat.com/show_bug.cgi?id=2413101 | Exploit Issue Tracking Vendor Advisory |
Configurations
History
No history.
Information
Published : 2026-03-26 22:16
Updated : 2026-06-17 08:32
NVD link : CVE-2025-12805
Mitre link : CVE-2025-12805
CVE.ORG link : CVE-2025-12805
JSON object : View
Products Affected
redhat
- openshift_ai
CWE
CWE-653
Improper Isolation or Compartmentalization
