Servers and applications
CVE-2026-48746
OpenAI API Auth Bypass
- Severity
- Critical 9.1
- Published
- 2 Jun 2026
- Last changed
- 25 Oct 2026
- Added to UpHeron
- 3 Nov 2026
- Fixed in
- 0.22.0
- Exploit chance
- 1.2% in the next 30 daysHigher than 67% of CVEs. EPSS by FIRST, 19 Nov 2026
- Attack
- Over the network · No login needed · No user action needed
- Attacker can
- Read data · Take it down
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H- Also known as
- GHSA-94f4-hr76-p5j6
- Sources
- NVD, Project advisories (GitHub)
Description
A vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware, which was discovered during @x41sec's source code audit. It allows to use the API without providing the configured VLLM_API_KEY or --api-key.
In https://github.com/vllm-project/vllm/blob/v0.14.0/vllm/entrypoints/openai/api_server.py#L689-L692 the url_path is taken from the URL, which is reconstructed by _starlette_ based on the request scope.
The request scope includes the request's Host: header and reconstructs the URL as shown below:
Neither starlette nor any of the ASGI servers (including uvicorn, which vllm uses) properly filter the Host: header for invalid characters. This allows an attacker to include special URL characters such as / or ? in the Host: header and thereby control the reconstructed URL and it's .path attribute.
Affected software
| Software | Affected versions |
|---|---|
vLLMServers and applications · cpe:a:vllm:vllm |
|
vLLMServers and applications · github:vllm-project/vllm |
|
About vLLM
open-source software for large language model inference
- Docker Hub pulls
- 44,195,225Docker Hub, 15 Nov 2026
- GitHub stars
- 96,943GitHub, 15 Nov 2026
- Forks
- 24,836GitHub, 15 Nov 2026
- Latest release
- v0.33.0rc3GitHub, 15 Nov 2026
- Released
- 2 Nov 2026GitHub
- License
- Apache Software License 2.0Wikidata
- First published on GitHub
- 9 Feb 2023GitHub
Website Source code Docker image
Vulnerabilities in vLLM
- In our list
- 169
- Published in the last 12 months
- 150
- Critical, last 12 months
- 6
- High, last 12 months
- 63
- Known exploited
- 0
- CVE-2026-130686vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image RequestsHigh 8.7 18 Nov 2026
- CVE-2026-130684vLLM before 0.33.0 Path Traversal via speculators_config verifier.name_or_pathMedium 5.3 18 Nov 2026
- CVE-2026-130685vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token IDHigh 8.7 18 Nov 2026
- GHSA-xgh8-qwjh-q853/v1/systemone bypasses the --trust-request-chat-template gateMedium 6.5 18 Nov 2026
- CVE-2026-129356vllm-project vllm Common Prefix single_type_kv_cache_manager.py race conditionLow 2.3 15 Nov 2026
- CVE-2026-126394vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_framesMedium 6.9 13 Nov 2026
References
- NVD https://nvd.nist.gov/vuln/detail/CVE-2026-48746
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-48746
- GitHub Advisory Database https://github.com/advisories/GHSA-94f4-hr76-p5j6
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6