CVE-2025-12805 | Red Hat OpenShift AI Llama Stack Service improper isolation or compartmentalization (RHSA-2026:2106)

VDB-353763 · CVE-2025-12805 · RHSA-2026:2106 RED HAT OPENSHIFT AI LLAMA STACK SERVICE IMPROPER ISOLATION OR COMPARTMENTALIZATION HISTORYDIFFRELATEJSONXMLCTI CVSS Meta Temp Score Current Exploit Price (≈) CTI Interest Score 7.2 $5k-$25k 1.10+ Summaryinfo 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. Detailsinfo 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 03/26/2026). There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product. Productinfo Type Virtualization Software Vendor Red Hat Name OpenShift AI License open-source Website Vendor: https://www.redhat.com/ CPE 2.3info 🔒 CPE 2.2info 🔒 CVSSv4info VulDB Vector: 🔒 VulDB Reliability: 🔍 CVSSv3info VulDB Meta Base Score: 7.2 VulDB 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): 🔒 CVSSv2info 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: 🔍 Exploitinginfo Class: Improper isolation or compartmentalization CWE: CWE-653 CAPEC: 🔒 ATT&CK: 🔒 Physical: No Local: No Remote: Yes Availability: 🔒 Status: Not defined Price Prediction: 🔍 Current Price Estimation: 🔒 0-Day Unlock Unlock Unlock Unlock Today Unlock Unlock Unlock Unlock Threat Intelligenceinfo Interest: 🔍 Active Actors: 🔍 Active APT Groups: 🔍 Countermeasuresinfo Recommended: no mitigation known Status: 🔍 0-Day Time: 🔒 Timelineinfo 11/06/2025 CVE reserved 03/26/2026 +140 days Advisory disclosed 03/26/2026 +0 days VulDB entry created 03/26/2026 +0 days VulDB entry last update Sourcesinfo Vendor: redhat.com Advisory: RHSA-2026:2106 Status: Confirmed CVE: CVE-2025-12805 (🔒) GCVE (CVE): GCVE-0-2025-12805 GCVE (VulDB): GCVE-100-353763 Entryinfo Created: 03/26/2026 23:15 Changes: 03/26/2026 23:15 (62) Complete: 🔍 Cache ID: 99:24B:101 Discussion No comments yet. Languages: en. Please log in to comment. ◂ PreviousOverviewNext ▸