# CVE-2025-6920: Ai-inference-server: authentication bypass via unprotected inference endpoint in api

> Attackers can bypass authentication on the inference endpoint to access protected model features and backend resources without an API key.

- **Severity:** Medium 5.3 (`CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 1 Jul 2025
- **Updated:** 20 Nov 2025
- **Also known as:** GHSA-5qf8-7rm9-wfxp

## What is CVE-2025-6920?

CVE-2025-6920 is a medium-severity authentication bypass vulnerability in Red Hat AI Inference Server, published on 1 Jul 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.

### Official description

A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/* endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows unauthorized users to access the same inference features available on protected endpoints, potentially exposing sensitive functionality or allowing unintended access to backend resources.

Weakness: CWE-306 (Missing Authentication for Critical Functionality)

## Which versions are affected by CVE-2025-6920?

It affects 1 product.


Products: Redhat Ai Inference Server.

## How do I fix CVE-2025-6920?

No fix has been published for CVE-2025-6920 yet. Limit exposure of the affected software until one is available.

## Is CVE-2025-6920 being exploited?

There is no known exploitation of CVE-2025-6920 in the wild and no public exploit code.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2025-6920 and fix it if it is affected.

What it is: CVE-2025-6920 is a medium-severity authentication bypass vulnerability in Red Hat AI Inference Server, published on 1 Jul 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.
Exploitation: There is no known exploitation of CVE-2025-6920 in the wild and no public exploit code.

Affected product: Red Hat AI Inference Server. 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-2025-6920/ (Markdown: https://insights.sbomify.com/CVE-2025-6920/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2025-6920
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2025-6920
- OSV: https://osv.dev/vulnerability/CVE-2025-6920

---
From sbomify Insights: https://insights.sbomify.com/CVE-2025-6920/
Summaries are generated and may contain mistakes; the official description above is the record.