Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| Red Hat / Red Hat OpenShift AI 2.25 | unaffected sha256:c0d95dfbae20e87113ffb81026d379bb63ad300447df98b27d1bf9a83b084744 before * |
| Red Hat / Red Hat OpenShift AI 2.25 | unaffected sha256:1d258fe98c2477e4256a9b936f412f2501fb7ca9e3b810347f9712e0d5ce5c92 before * |
| Red Hat / Red Hat OpenShift AI (RHOAI) | unaffected |
| Red Hat / Red Hat OpenShift AI (RHOAI) | unaffected |
CWE
CWE-653
References
- https://access.redhat.com/errata/RHSA-2026:2106
- https://access.redhat.com/errata/RHSA-2026:2695
- https://access.redhat.com/security/cve/CVE-2025-12805
- https://bugzilla.redhat.com/show_bug.cgi?id=2413101
ADP enrichment
No English description supplied.
No references supplied.