HIGHVulnerability
Verified
Global
NVD HIGH: CVE-2025-12805 — A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vuln...
Thursday, March 26, 2026 at 10:16 PM UTC·Source: NIST NVD
Updated: Thursday, April 2, 2026 at 05:46 PM UTC
Executive Summary
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 sen
Analysis
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.
CVSS Score: 8.1. Published: 2026-03-26T22:16:25.920.