Vulnerability Intelligence Report
vLLM: OpenAI auth bypass
CVE-2026-48746
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.
No Active Exploit Signals
CVSS Base Score
9.1
CRITICAL
Exploitability:3.9
Impact Score:5.2
EPSS Probability:1.15%
Executive Threat Verdict
Evaluating...
Evaluating Threat Landscape...
Assessing known weaponization, exploitation telemetry, and federal advisories.
Attack Surface
—
Authentication
—
Weaponization
—
SSVC Action
—
Weaknesses (CWE)
CWE-444 ↗CWE-444: Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling')
Affected Products & Versions
| Vendor | Product | Affected Versions |
|---|---|---|
| vllm-project | vllm | >= 0.3.0, < 0.22.0 (affected) |
References & Technical Advisories
No reference links found.
Threat Intelligence Signals
EPSS Score
1.152%
GitHub Advisory
Identity & Timeline
| Status | PUBLISHED |
| Assigning Authority | GitHub, Inc. · Vendor · USA |
| Reserved | 2026-05-22T19:10:35 |
| Published | 2026-06-22T21:57:28 |
| Last Updated | 2026-09-16T12:04:20 |
Community Chatter & Buzz