CVE-2025-48956 | vLLM API endpoints vulnerable to Denial of Service Attacks

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.

Published: 2025-08-21 Last update: 2025-10-09 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2025-48956 is rated Moderate Risk (47.6/100): CVSS High severity, with medium exploitation likelihood (EPSS 0.27%). Review affected assets and schedule remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2025-48956

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-03-27 0.37% 0.27% -0.10%
2 2026-03-17 0.32% 0.37% +0.05%
3 2026-01-17 — 0.32% —

Full EPSS history (6 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-48956

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
7.5 3.1 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 3.6 [email protected]

Weakness enumeration for CVE-2025-48956

GitHub Security Advisory for CVE-2025-48956

GHSA-rxc4-3w6r-4v47 · Severity: high · Ecosystem: pip — vllm API endpoints vulnerable to Denial of Service Attacks

OS Trackers for CVE-2025-48956

vendor priority summary link
redhat high — https://access.redhat.com/security/cve/CVE-2025-48956

Affected software / configurations for CVE-2025-48956

Vendor Product Version Raw CPE
vllm vllm >= 0.1.0, < 0.10.1.1 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

References for CVE-2025-48956

cvelogic Threat Intelligence