CVE-2026-48746: vLLM is an inference and serving engine for large language models (LLMs)
CVE-2026-48746 is a critical-severity flaw (CVSS 9.1) affecting vllm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
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.
Why this priority
- Critical severity
- CISA SSVC: public proof of concept
- Remotely exploitable, no login, no user action
A fixed release or distro patch exists.
Last updated 2026-10-25 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score
Am I affected?
Timeline
- Published CVE record published
- Updated Record last modified
Exact fixes by distribution
Public exploits and detection
Public code exists for this CVE. Treat unpatched systems as at risk, and only run PoCs in a lab.
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.
Quick answers
How do I fix CVE-2026-48746?
vllm: upgrade to 0.22.0. Exact commands for each OS are on this page.
Is CVE-2026-48746 being exploited?
CVE-2026-48746 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.
What does CVE-2026-48746 affect?
CVE-2026-48746 affects vllm. Severity is critical (CVSS 9.1). 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 Authenticat
How urgent is CVE-2026-48746?
Priority 57/100. Critical severity; CISA SSVC: public proof of concept; Remotely exploitable, no login, no user action
Software pages
OpenAI and LLM tools vulnerabilities
Related CVEs
- CVE-2026-54232 HIGH 8.8 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-41523 HIGH 7.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54236 MEDIUM 5.3 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-53923 HIGH 7.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54235 MEDIUM 6.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)