CVE-2025-12805
Last modified
CVE-2025-12805 is a high-severity vulnerability rated 8.1/10 on the CVSS scale. 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. EPSS estimates a 0.38% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Redhat | Openshift Ai | 2.25 |
References
- https://access.redhat.com/errata/RHSA-2026:2106Vendor Advisory
- https://access.redhat.com/errata/RHSA-2026:2695Vendor Advisory
- https://access.redhat.com/security/cve/CVE-2025-12805Vendor Advisory
- https://bugzilla.redhat.com/show_bug.cgi?id=2413101Exploit, Issue Tracking, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-12805?
How severe is CVE-2025-12805?
How do I fix CVE-2025-12805?
Are you affected by CVE-2025-12805?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
