Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

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

Quick assessment

Affected
Red Hat Red Hat OpenShift AI 2.25
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Llama Stack是Meta Llama开源的一个简化人工智能应用开发的核心构建模块。 Llama Stack存在安全漏洞，该漏洞源于缺少网络策略限制对llama-stack服务端点的访问，可能导致未经授权访问部署在其他命名空间中的Llama Stack服务。

CVSS 8.1 · High EPSS 0.38% · P30
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-12805

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
Llama-stack-k8s-operator: llama stack service exposed across namespaces due to missing networkpolicy
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
不充分的划分
Source: CVE Program / CVE List V5
Vulnerability Title
Llama Stack 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Llama Stack是Meta Llama开源的一个简化人工智能应用开发的核心构建模块。 Llama Stack存在安全漏洞，该漏洞源于缺少网络策略限制对llama-stack服务端点的访问，可能导致未经授权访问部署在其他命名空间中的Llama Stack服务。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
Red Hat Red Hat OpenShift AI 2.25 sha256:c0d95dfbae20e87113ffb81026d379bb63ad300447df98b27d1bf9a83b084744 ~ * cpe:/a:redhat:openshift_ai:2.25::el9
Red Hat Red Hat OpenShift AI 2.25 sha256:1d258fe98c2477e4256a9b936f412f2501fb7ca9e3b810347f9712e0d5ce5c92 ~ * cpe:/a:redhat:openshift_ai:2.25::el9
Red Hat Red Hat OpenShift AI (RHOAI) - cpe:/a:redhat:openshift_ai
Red Hat Red Hat OpenShift AI (RHOAI) - cpe:/a:redhat:openshift_ai

II. Public POCs for CVE-2025-12805

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2025-12805

请登录查看更多情报信息。

Vendor Advisories for CVE-2025-12805 (4)

Same Patch Batch · Red Hat · 2026-03-26 · 16 CVEs total

CVE-2026-1961 8.0 HIGH Forman: foreman: remote code execution via command injection in websocket proxy
CVE-2026-2436 6.5 MEDIUM Libsoup: libsoup: denial of service via use-after-free in soupserver during tls handshake
CVE-2026-3121 6.5 MEDIUM Keycloak: org.keycloak/keycloak-services: keycloak: privilege escalation via manage-client
CVE-2026-4887 6.1 MEDIUM Gimp: gimp:memory disclosure and denial of service via specially crafted pcx image
CVE-2026-4897 5.5 MEDIUM Polkit: polkit: denial of service via unbounded input processing through standard input
CVE-2026-2272 4.3 MEDIUM Gimp: gimp: memory corruption due to integer overflow in ico file handling
CVE-2026-3190 4.3 MEDIUM Keycloak: keycloak: information disclosure via improper role enforcement in uma 2.0 protec
CVE-2026-2271 3.3 LOW Gimp: gimp: denial of service via crafted psp image file
CVE-2026-0968 3.1 LOW Libssh: libssh: denial of service due to malformed sftp message
CVE-2026-4874 3.1 LOW Org.keycloak.protocol.oidc.grants: org.keycloak.services.managers: keycloak: server-side r
CVE-2026-2239 2.8 LOW Gimp: gimp: application crash (dos) via crafted psd file due to heap-buffer-overflow
CVE-2026-0965 Libssh: libssh: denial of service via improper configuration file handling
CVE-2026-0967 Libssh: libssh: denial of service via inefficient regular expression processing
CVE-2026-0964 Libssh: improper sanitation of paths received from scp servers
CVE-2026-0966 Libssh: libssh: denial of service via zero-length input in ssh_get_hexa()

IV. Related Vulnerabilities

Same product: Red Hat OpenShift AI 2.25
Same vendor: Red Hat
Same weakness: CWE-653

V. Comments for CVE-2025-12805

No comments yet

Leave a comment