# vLLM: OpenAI auth bypass

Advisory record · `GHSA-94f4-hr76-p5j6`

- **Identifiers:** `GHSA-94f4-hr76-p5j6` · `CVE-2026-48746` · `PYSEC-2026-226`
- **State:** Confirmed
- **Severity:** CVSS 9.1 Critical
- **Critical:** Yes: CVSS 9+
- **Weakness (CWE):** [CWE-444](https://cwe.mitre.org/data/definitions/444.html) · [CWE-501](https://cwe.mitre.org/data/definitions/501.html)
- **Tags:** [HTTP request smuggling](https://agentprime.io/advisories/tag/request-smuggling.md) · [CWE-501](https://agentprime.io/advisories/tag/cwe-501.md)
- **Published:** 16 Jun 2026
- **Updated:** 10 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 16 Jun 2026, 17:36 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Critical

Critical, because:

- CVSS score 9.1: 9.0 or more.

How we decide what’s critical: <https://agentprime.io/advisories/critical.md>

## Affected packages

- `vllm` (PyPI): affected `>=0.3.0, <0.22.0`; fixed in `0.22.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> vllm versions 0.3.0 up to 0.22.0 have an authentication bypass in the OpenAI API server. An attacker with network access can send a crafted Host header to use the API without the configured API key. Upgrade to vllm 0.22.0. Deployments behind an RFC-conforming web server such as nginx are not affected.

Written 4 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 9.1 Critical, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.012, the 67th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:29 UTC: First seen by agentprime
- 31 Oct 2026, 14:29 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-94f4-hr76-p5j6)

## Sources

- [GitHub Advisory Database: GHSA-94f4-hr76-p5j6](https://github.com/advisories/GHSA-94f4-hr76-p5j6)
- [OSV: GHSA-94f4-hr76-p5j6](https://osv.dev/vulnerability/GHSA-94f4-hr76-p5j6)
- <https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-48746>
- <https://github.com/vllm-project/vllm/pull/43426>
- <https://x41-dsec.de/lab/advisories/x41-2026-002-starlette>
- <https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-48746.json>
- <https://github.com/vllm-project/vllm>
- <https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-226.yaml>
- <https://bugzilla.redhat.com/show_bug.cgi?id=2491581>
- <https://access.redhat.com/security/cve/CVE-2026-48746>
- <https://access.redhat.com/errata/RHSA-2026:61629>
- <https://access.redhat.com/errata/RHSA-2026:61627>
- <https://access.redhat.com/errata/RHSA-2026:43038>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-94f4-hr76-p5j6>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-94f4-hr76-p5j6/>. Everything for agents: <https://agentprime.io/llms.txt>.