Red Hat OpenShift AI Llama Stack Service improper isolation or compartmentalization
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 7.2 | $5k-$25k | 0.00 |
Summary
A vulnerability marked as critical has been reported in Red Hat OpenShift AI. This vulnerability affects unknown code of the component Llama Stack Service. Performing a manipulation results in improper isolation or compartmentalization. This vulnerability was named CVE-2025-12805. The attack may be initiated remotely. There is no available exploit.
Details
A vulnerability classified as critical has been found in Red Hat OpenShift AI (the affected version is unknown). This affects an unknown code of the component Llama Stack Service. The manipulation with an unknown input leads to a improper isolation or compartmentalization vulnerability. CWE is classifying the issue as CWE-653. The product does not properly compartmentalize or isolate functionality, processes, or resources that require different privilege levels, rights, or permissions. This is going to have an impact on confidentiality, integrity, and availability. The summary by CVE is:
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.
It is possible to read the advisory at access.redhat.com. This vulnerability is uniquely identified as CVE-2025-12805 since 11/06/2025. The exploitability is told to be easy. It is possible to initiate the attack remotely. The technical details are unknown and an exploit is not publicly available. The pricing for an exploit might be around USD $5k-$25k at the moment (estimation calculated on 03/27/2026).
There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.
The vulnerability is also documented in the vulnerability database at EUVD (EUVD-2025-209086). Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.
Product
Type
Vendor
Name
License
Website
- Vendor: https://www.redhat.com/
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 7.2VulDB Meta Temp Score: 7.2
VulDB Base Score: 6.3
VulDB Temp Score: 6.3
VulDB Vector: 🔒
VulDB Reliability: 🔍
CNA Base Score: 8.1
CNA Vector (redhat): 🔒
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Improper isolation or compartmentalizationCWE: CWE-653
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
EPSS Score: 🔒
EPSS Percentile: 🔒
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: no mitigation knownStatus: 🔍
0-Day Time: 🔒
Timeline
11/06/2025 CVE reserved03/26/2026 Advisory disclosed
03/26/2026 VulDB entry created
03/27/2026 VulDB entry last update
Sources
Vendor: redhat.comAdvisory: RHSA-2026:2106
Status: Confirmed
CVE: CVE-2025-12805 (🔒)
GCVE (CVE): GCVE-0-2025-12805
GCVE (VulDB): GCVE-100-353763
EUVD: 🔒
Entry
Created: 03/26/2026 23:15Updated: 03/27/2026 06:18
Changes: 03/26/2026 23:15 (62), 03/27/2026 06:18 (1)
Complete: 🔍
Cache ID: 216::103
Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.
No comments yet. Languages: en.
Please log in to comment.