# CVE-2026-48746: vLLM authentication bypass in OpenAI API via Host header injection

Source: https://junglewise.ai/threats/cve-2026-48746-vllm-authentication-bypass-in-openai-api-via-host-header  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-22. Updated: 2026-06-22  
License: CC BY 4.0 with a link back

CVE-2026-48746 · Severity: critical · CVSS 9.1 · Published 2026-06-22

vLLM is an engine used to serve Large Language Models (LLMs) via an API. A security flaw allows attackers to bypass the required API key authentication by sending specially crafted web requests. This could allow unauthorized users to access and use expensive AI resources or sensitive model endpoints without permission.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-48746 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-48746 being exploited in the wild.

**How severe is CVE-2026-48746?** Critical severity, with a CVSS score of 9.1, published 22 June 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0.3.0,fixed=0.22.0.

**Is there a fix for CVE-2026-48746?** Yes. vllm (PyPI): upgrade to 0.22.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-48746 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-48746?** Check whether you run vllm (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- vllm (PyPI): upgrade to 0.22.0 or later

  ```sh
  pip install "vllm>=0.22.0"
  ```


## Technical details

An authentication bypass exists in vLLM's OpenAI API server due to inconsistent interpretation of HTTP requests. The `AuthenticationMiddleware` reconstructs the request URL using the `Host` header provided by the ASGI server (such as uvicorn). Because these servers do not strictly validate the `Host` header, an attacker can inject special characters (like `/` or `?`) into the header to manipulate the reconstructed `url.path` used for security checks. While the middleware sees a path that appears to bypass authentication requirements, the underlying Starlette router still directs the request to the intended protected endpoint. This allows remote, unauthenticated attackers to access the API without a valid `VLLM_API_KEY`. The issue is mitigated if vLLM is deployed behind an RFC-conforming reverse proxy like Nginx.

## Affected products

- vllm-project vLLM >= 0.3.0, < 0.22.0

## Identifiers

- CVE-2026-48746
- GHSA-94f4-hr76-p5j6
- PYSEC-2026-226

## Timeline

- 2026-01-27: other: Issue identified during source code audit
- 2026-05-22: other: Pull request submitted to fix path extraction
- 2026-06-22: advisory: NVD and GitHub advisories published

## References

- [https://github.com/vllm-project/vllm/pull/43426](https://github.com/vllm-project/vllm/pull/43426)
- [https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6](https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6)
- [https://x41-dsec.de/lab/advisories/x41-2026-002-starlette](https://x41-dsec.de/lab/advisories/x41-2026-002-starlette)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)