high8.1
CVE-2025-12805
A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator.
Impact
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
| Vendor | Product | Affected versions |
|---|---|---|
| Redhat | Openshift Ai | Version 2.25 |