Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.
Severity (CVSS)
| Base score | 9.1 |
|---|---|
| Severity | Critical |
| Version | CVSS 3.1 |
| Vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H |
| Provided by | CNA |
Weaknesses
- CWE-444 — CWE-444: Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling')
Affected products
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.3.0, < 0.22.0 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6 (x_refsource_CONFIRM)
- https://github.com/vllm-project/vllm/pull/43426 (x_refsource_MISC)
- https://x41-dsec.de/lab/advisories/x41-2026-002-starlette (x_refsource_MISC)
Generated from the official CVE List on 23 Jun 2026 10:05 UTC.