HIGH · 7.5

CVE-2025-48956

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request w...

Vulnerability Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.

CVSS Score

7.5

HIGH

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH

Affected Products

VendorProductVersions
VllmVllm>= 0.1.0, < 0.10.1.1

Related Weaknesses (CWE)

References

FAQ

What is CVE-2025-48956?

CVE-2025-48956 is a vulnerability with a CVSS score of 7.5 (HIGH). vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request w...

How severe is CVE-2025-48956?

CVE-2025-48956 has been rated HIGH with a CVSS base score of 7.5/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2025-48956?

Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.