How severe is CVE-2025-12805?

CVE-2025-12805 has a CVSS 3.x base score of 8.1, rated high severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability none.

Is CVE-2025-12805 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (30th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2025-12805?

CVE-2025-12805 affects Redhat Openshift Ai. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2025-12805?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.

Does CVE-2025-12805 have an EU (EUVD) identifier?

Yes. CVE-2025-12805 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-209086.

When was CVE-2025-12805 published?

CVE-2025-12805 was published on 2026-03-26 and last updated on 2026-06-17.

CVE-2025-12805

CVE-2025-12805 is a high-severity vulnerability in Redhat Openshift Ai with a CVSS 3.x base score of 8.1. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-653.

Key facts

Severity: High (CVSS 3.x base score 8.1)
EPSS exploit prediction: 0% (30th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2025-209086
Weakness: CWE-653
Affected product: Redhat Openshift Ai
Published: 2026-03-26
Last modified: 2026-06-17

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.

Frequently asked questions

What is CVE-2025-12805?: 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.
How severe is CVE-2025-12805?: CVE-2025-12805 has a CVSS 3.x base score of 8.1, rated high severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability none.
Is CVE-2025-12805 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (30th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2025-12805?: CVE-2025-12805 affects Redhat Openshift Ai. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2025-12805?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
Does CVE-2025-12805 have an EU (EUVD) identifier?: Yes. CVE-2025-12805 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-209086.
When was CVE-2025-12805 published?: CVE-2025-12805 was published on 2026-03-26 and last updated on 2026-06-17.

References

Affected products (1)

cpe:2.3:a:redhat:openshift_ai:2.25:*:*:*:*:*:*:*

More vulnerabilities in Redhat Openshift Ai

CVE-2026-42271 — High (CVSS 8.8): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before…
CVE-2024-7557 — High (CVSS 8.8): A vulnerability was found in OpenShift AI that allows for authentication bypass and privilege escalation across models…
CVE-2026-5483 — High (CVSS 8.5): A flaw was found in odh-dashboard in Red Hat Openshift AI. This vulnerability in the `odh-dashboard` component of Red…
CVE-2026-1462 — High (CVSS 7.8): A vulnerability in the `TFSMLayer` class of the `keras` package, version 3.13.0, allows attacker-controlled TensorFlow…

All CVEs affecting Redhat Openshift Ai →

Other CWE-653 vulnerabilities

CVE-2026-4692 — Critical (CVSS 10.0): Sandbox escape in the Responsive Design Mode component. This vulnerability was fixed in Firefox 149, Firefox ESR…
CVE-2025-1974 — Critical (CVSS 9.8): A security issue was discovered in Kubernetes where under certain conditions, an unauthenticated attacker with access…
CVE-2024-33768 — Critical (CVSS 9.8): lunasvg v2.3.9 was discovered to contain a segmentation violation via the component composition_solid_source_over.
CVE-2026-0542 — Critical (CVSS 9.2): ServiceNow has addressed a remote code execution vulnerability that was identified in the ServiceNow AI platform. This…
CVE-2025-4083 — Critical (CVSS 9.1): A process isolation vulnerability in Thunderbird stemmed from improper handling of javascript: URIs, which could allow…
CVE-2025-5476 — High (CVSS 8.8): Sony XAV-AX8500 Bluetooth Improper Isolation Authentication Bypass Vulnerability. This vulnerability allows…

Browse all CWE-653 vulnerabilities →