How severe is CVE-2026-48746?

CVE-2026-48746 has a CVSS 3.x base score of 9.1, rated critical severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity none, and availability high.

Is CVE-2026-48746 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (54th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2026-48746?

CVE-2026-48746 affects Vllm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2026-48746?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its critical severity, prioritise patching exposed systems.

Does CVE-2026-48746 have an EU (EUVD) identifier?

Yes. CVE-2026-48746 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-38401.

When was CVE-2026-48746 published?

CVE-2026-48746 was published on 2026-06-22 and last updated on 2026-07-07.

CVE-2026-48746

CVE-2026-48746 is a critical-severity vulnerability in Vllm with a CVSS 3.x base score of 9.1. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-444.

Key facts

Severity: Critical (CVSS 3.x base score 9.1)
EPSS exploit prediction: 1% (54th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2026-38401
Weakness: CWE-444
Affected product: Vllm
Published: 2026-06-22
Last modified: 2026-07-07

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.

Frequently asked questions

What is 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.
How severe is CVE-2026-48746?: CVE-2026-48746 has a CVSS 3.x base score of 9.1, rated critical severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity none, and availability high.
Is CVE-2026-48746 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (54th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2026-48746?: CVE-2026-48746 affects Vllm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-48746?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its critical severity, prioritise patching exposed systems.
Does CVE-2026-48746 have an EU (EUVD) identifier?: Yes. CVE-2026-48746 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-38401.
When was CVE-2026-48746 published?: CVE-2026-48746 was published on 2026-06-22 and last updated on 2026-07-07.

References

Affected products (1)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

More vulnerabilities in Vllm

CVE-2025-32444 — Critical (CVSS 10.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and…
CVE-2026-22778 — Critical (CVSS 9.8): vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid…
CVE-2025-47277 — Critical (CVSS 9.8): vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4…
CVE-2024-11041 — Critical (CVSS 9.8): vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses…
CVE-2025-29783 — Critical (CVSS 9.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use…
CVE-2026-54232 — High (CVSS 8.8): vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is…

All CVEs affecting Vllm →

Other CWE-444 (HTTP Request/Response Smuggling) vulnerabilities

CVE-2025-1867 — Critical (CVSS 10.0): Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling') vulnerability in ithewei libhv allows…
CVE-2022-22536 — Critical (CVSS 10.0): SAP NetWeaver Application Server ABAP, SAP NetWeaver Application Server Java, ABAP Platform, SAP Content Server 7.53…
CVE-2018-3907 — Critical (CVSS 10.0): An exploitable vulnerability exists in the REST parser of video-core's HTTP server of the Samsung SmartThings Hub…
CVE-2025-55315 — Critical (CVSS 9.9): Inconsistent interpretation of http requests ('http request/response smuggling') in ASP.NET Core allows an authorized…
CVE-2020-15049 — Critical (CVSS 9.9): An issue was discovered in http/ContentLengthInterpreter.cc in Squid before 4.12 and 5.x before 5.0.3. A Request…
CVE-2026-13763 — Critical (CVSS 9.8): Inconsistent interpretation of HTTP/2 requests in AWS Application Load Balancer with AWS WAF enabled might allow remote…

Browse all CWE-444 (HTTP Request/Response Smuggling) vulnerabilities →