Unauthorized Access Vulnerability in Red Hat OpenShift AI Llama Stack Operator
CVE-2025-12805

8.1HIGH

Key Information:

Vendor

Red Hat
Status
Red Hat Openshift Ai 2.25
Red Hat Openshift Ai (rhoai)
Vendor
CVE Published:
26 March 2026

What is CVE-2025-12805?

A flaw in Red Hat OpenShift AI's Llama Stack Operator enables unauthorized users to bypass namespace barriers, allowing them to access Llama Stack services directly through network requests. This lack of a NetworkPolicy permits users in one namespace to interact with Llama Stack instances belonging to other namespaces, potentially exposing sensitive data and functionalities to unauthorized parties.

Affected Version(s)

Red Hat OpenShift AI 2.25 sha256:c0d95dfbae20e87113ffb81026d379bb63ad300447df98b27d1bf9a83b084744

Red Hat OpenShift AI 2.25 sha256:1d258fe98c2477e4256a9b936f412f2501fb7ca9e3b810347f9712e0d5ce5c92

References

https://access.redhat.com/errata/RHSA-2026:2106
vendor-advisoryx_refsource_REDHAT
https://access.redhat.com/errata/RHSA-2026:2695
vendor-advisoryx_refsource_REDHAT
https://access.redhat.com/security/cve/CVE-2025-12805
vdb-entryx_refsource_REDHAT

CVSS V3.1

Score:
8.1
Severity:
HIGH
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
Low
User Interaction:
None
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.