Menu

Star on GitHub · 3.2k

CVE-2025-12805

8.1 · HIGH

A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator.

Published Mar 26, 2026CWE-653EPSS 0.38%

Overview

CVE-2025-12805 is a high-severity vulnerability. It was published on March 26, 2026 and has a CVSS 3.1 base score of 8.1 (HIGH).

This vulnerability has a CVSS 3.1 base score of 8.1, rated HIGH. It can be exploited remotely over the network. Some level of privileges is required for exploitation.

Technical 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.

Remediation

Check the references section for vendor advisories, patches, and mitigation guidance. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

Frequently asked questions

What is CVE-2025-12805?

CVE-2025-12805 is a high-severity vulnerability. It was published on March 26, 2026 and has a CVSS 3.1 base score of 8.1 (HIGH).

How severe is CVE-2025-12805?

This vulnerability has a CVSS 3.1 base score of 8.1, rated HIGH. It can be exploited remotely over the network. Some level of privileges is required for exploitation.

How do I fix or remediate CVE-2025-12805?

Check the references section for vendor advisories, patches, and mitigation guidance. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

How can CyberStrike help with CVE-2025-12805?

CyberStrike is an open-source, AI-augmented pentesting engine. Rather than flag a version number, it tests whether an issue like CVE-2025-12805 is actually reachable in your own applications and APIs, then verifies each finding before reporting it. That tells you if the weakness is a real, exploitable risk in your environment or a false positive you can safely deprioritize.

Related HIGH CVEs from 2025

View all