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

> Attackers in one namespace can access and manipulate Llama Stack services in other namespaces due to missing network policies.

- **Severity:** High 8.1 (`CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N`)
- **Exploited in the wild:** Not known
- **Login needed:** Any signed-in user
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 26 Mar 2026
- **Updated:** 31 Mar 2026
- **Also known as:** GHSA-cq3g-qvxc-ghr5

## What is CVE-2025-12805?

CVE-2025-12805 is a high-severity missing authorization vulnerability in Red Hat OpenShift AI (RHOAI), published on 26 Mar 2026. Any signed-in user can exploit it over the network, with no action from the victim.

### Official 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.

Weakness: CWE-653 (Improper Isolation or Compartmentalization)

## Which versions are affected by CVE-2025-12805?

It affects 1 product.


Products: Redhat Openshift Ai.

## How do I fix CVE-2025-12805?

No fix has been published for CVE-2025-12805 yet. Limit exposure of the affected software until one is available.

## Is CVE-2025-12805 being exploited?

There is no known exploitation of CVE-2025-12805 in the wild and no public exploit code.

## Other vulnerabilities in Red Hat OpenShift AI (RHOAI)

- [CVE-2024-7557](https://insights.sbomify.com/CVE-2024-7557/): Odh-dashboard: odh-model-controller: cross-model authentication bypass in openshift ai (high 8.8)
- [CVE-2026-5483](https://insights.sbomify.com/CVE-2026-5483/): Odh-dashboard: odh dashboard kubernetes service account exposure (high 8.5)
- [CVE-2026-15154](https://insights.sbomify.com/CVE-2026-15154/): Denial of service in Red Hat OpenShift AI 2.25 (medium 6.5)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2025-12805 and fix it if it is affected.

What it is: CVE-2025-12805 is a high-severity missing authorization vulnerability in Red Hat OpenShift AI (RHOAI), published on 26 Mar 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Exploitation: There is no known exploitation of CVE-2025-12805 in the wild and no public exploit code.

Affected product: Red Hat OpenShift AI (RHOAI). No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2025-12805/ (Markdown: https://insights.sbomify.com/CVE-2025-12805/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2025-12805
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2025-12805
- OSV: https://osv.dev/vulnerability/CVE-2025-12805

---
From sbomify Insights: https://insights.sbomify.com/CVE-2025-12805/
Summaries are generated and may contain mistakes; the official description above is the record.