CVE-2025-12805

Llama-stack-k8s-operator: llama stack service exposed across namespaces due to missing networkpolicy

State
Published
Severity
8.1 High
Published
Mar 26, 2026
Updated
Mar 31, 2026
Reserved
Nov 6, 2025

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
3.18.1 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:Nredhat

Weaknesses

  • CWE-653 Improper Isolation or Compartmentalization

Affected Products

ProductVersions
Red Hat OpenShift AI 2.25Red Hat
  • sha256:c0d95dfbae20e87113ffb81026d379bb63ad300447df98b27d1bf9a83b084744 and laterNot affected
Red Hat OpenShift AI 2.25Red Hat
  • sha256:1d258fe98c2477e4256a9b936f412f2501fb7ca9e3b810347f9712e0d5ce5c92 and laterNot affected
Red Hat OpenShift AI (RHOAI)Red Hat
    Red Hat OpenShift AI (RHOAI)Red Hat

      References

      Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.