VulnerabilityAnalyzed

CVE-2025-48956

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.

HIGH 7.5EPSS 0.56%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.56%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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 3.1: 7.5 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS: 0.56% probability · 45th percentile
CISA KEV: Not listed
Weakness: CWE-400
Affected: vllm/vllm
Source: security-advisories@github.com

References

https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944Patch
https://github.com/vllm-project/vllm/pull/23267Issue Tracking, Patch
https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47Vendor Advisory

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.