Unauthorized Namespace Access via RHOAI Llama-Stack Operator - CVE-2025-12805
CVE-2025-12805 Published on March 26, 2026

Llama-stack-k8s-operator: llama stack service exposed across namespaces due to missing networkpolicy
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 users Llama Stack instance and potentially view or manipulate sensitive data.

Vendor Advisory Vendor Advisory NVD

Vulnerability Analysis

CVE-2025-12805 can be exploited with network access, and requires small amount of user privileges. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to have a high impact on confidentiality and integrity, and no impact on availability.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
LOW
User Interaction:
NONE
Scope:
UNCHANGED
Confidentiality Impact:
HIGH
Integrity Impact:
HIGH
Availability Impact:
NONE

Timeline

Reported to Red Hat.

Made public. 55 days later.

Weakness Type

What is a Separation of Privilege Vulnerability?

The product does not sufficiently compartmentalize functionality or processes that require different privilege levels, rights, or permissions. When a weakness occurs in functionality that is accessible by lower-privileged users, then without strong boundaries, an attack might extend the scope of the damage to higher-privileged users.

CVE-2025-12805 has been classified to as a Separation of Privilege vulnerability or weakness.


Products Associated with CVE-2025-12805

Want to know whenever a new CVE is published for Red Hat Openshift Ai? stack.watch will email you.

Red Hat Openshift Ai
 

Affected Versions

Red Hat OpenShift AI 2.25: Red Hat OpenShift AI 2.25: Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI):

Exploit Probability

EPSS
0.03%
Percentile
9.90%

EPSS (Exploit Prediction Scoring System) scores estimate the probability that a vulnerability will be exploited in the wild within the next 30 days. The percentile shows you how this score compares to all other vulnerabilities.