CVE-2025-12805

Published: Mar 26, 2026 Last Modified: Mar 26, 2026
ExploitDB:
Other exploit source:
Google Dorks:
HIGH 8,1
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Scope: unchanged
Confidentiality: high
Integrity: high
Availability: none

Description

AI Translation Available

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.

EPSS (Exploit Prediction Scoring System)

Trend Analysis

EPSS (Exploit Prediction Scoring System)

Prevede la probabilità di sfruttamento basata su intelligence sulle minacce e sulle caratteristiche della vulnerabilità.

EPSS Score
0,0003
Percentile
0,1th
Updated

Single Data Point

Only one EPSS measurement is available for this CVE. Trend analysis requires multiple data points over time.

653

Improper Isolation or Compartmentalization

Draft
Abstraction: Class Structure: Simple
Common Consequences
Security Scopes Affected:
Access Control
Potential Impacts:
Gain Privileges Or Assume Identity Bypass Protection Mechanism
Applicable Platforms
All platforms may be affected
View CWE Details
https://access.redhat.com/errata/RHSA-2026:2106
https://access.redhat.com/errata/RHSA-2026:2106
https://access.redhat.com/errata/RHSA-2026:2695
https://access.redhat.com/errata/RHSA-2026:2695
https://access.redhat.com/security/cve/CVE-2025-12805
https://access.redhat.com/security/cve/CVE-2025-12805
https://bugzilla.redhat.com/show_bug.cgi?id=2413101
https://bugzilla.redhat.com/show_bug.cgi?id=2413101