Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD 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.
Priority
LOW
Exploitation
NONE
PoC
YES
Patch
NONE
Momentum
STABLE
If you run products in this scope, you should treat this CVE as relevant to your environment.
1 version affected across 1 product
CVE-2025-12805 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 namespa… https://www.cve.org/CVERecord?id=CVE-2025-12805
Post summary
A new vulnerability, CVE‑2025‑12805, has been discovered in Red Hat OpenShift AI’s llama‑stack‑operator, enabling unauthorized cross‑namespace access to Llama Stack services.
🟠 CVE-2025-12805 - High 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 re... https://www.thehackerwire.com/vulnerability/CVE-2025-12805/ https://t.co/2dG5giOmX9
Post summary
The tweet announces CVE‑2025‑12805, a high‑severity flaw in Red Hat OpenShift AI’s llama‑stack‑operator that permits unauthorized network access to services in other namespaces; no PoC, exploit, or active exploitation is reported.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | redhat | openshift_ai | 2.25 | - | - |