CVE-2025-12805 | Llama-stack-k8s-operator: llama stack service exposed across namespaces due to missing networkpolicy

Exp

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.

Published: 2026-03-26 Last update: 2026-04-30 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2025-12805 is rated Exploit Available (58.2/100): CVSS High severity, with low exploitation likelihood (EPSS 0.38%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2025-12805

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2025-12805

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-15 0.03% 0.38% +0.35%
2 2026-03-27 — 0.03% —

Full EPSS history (2 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-12805

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
8.1 3.1 HIGH
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:N)
Service keeps running; no real outage angle.
 2.8 5.2 [email protected]

Weakness enumeration for CVE-2025-12805

OS Trackers for CVE-2025-12805

vendor priority summary link
redhat high — https://access.redhat.com/security/cve/CVE-2025-12805

Affected software / configurations for CVE-2025-12805

Vendor Product Version Raw CPE
redhat openshift_ai 2.25 cpe:2.3:a:redhat:openshift_ai:2.25:*:*:*:*:*:*:*

References for CVE-2025-12805

cvelogic Threat Intelligence