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.
Weakness
The product does not properly compartmentalize or isolate functionality, processes, or resources that require different privilege levels, rights, or permissions.
Affected Software
| Name | Vendor | Start Version | End Version |
|---|---|---|---|
| Openshift_ai | Redhat | 2.25 (including) | 2.25 (including) |
| Red Hat OpenShift AI 2.25 | RedHat | rhoai/odh-llama-stack-k8s-operator-rhel9:1770224279 | * |
| Red Hat OpenShift AI 2.25 | RedHat | rhoai/odh-llama-stack-k8s-operator-rhel9:1770788315 | * |