CVE-2025-62426 | vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

Published: 2025-11-20 Last update: 2026-06-17 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2025-62426 is rated Low Risk (34/100): CVSS Medium severity, with low exploitation likelihood (EPSS 0.31%). Monitor for updates and reassess as exploit intelligence or EPSS changes.

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-2025-62426

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 2026-06-15 0.05% 0.31% +0.26%
2 2025-12-05 0.04% 0.05% +0.01%
3 2025-11-21 — 0.04% —

Full EPSS history (3 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-62426

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
6.5 3.1 MEDIUM
CVSS:3.1/AV:N/AC:L/PR:L/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:L)
A normal user session is enough; they don’t have to be admin.
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.
 2.8 3.6 [email protected]

Weakness enumeration for CVE-2025-62426

GitHub Security Advisory for CVE-2025-62426

GHSA-69j4-grxj-j64p · Severity: medium · Ecosystem: pip — vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

OS Trackers for CVE-2025-62426

vendor priority summary link
redhat medium — https://access.redhat.com/security/cve/CVE-2025-62426

Affected software / configurations for CVE-2025-62426

Vendor Product Version Raw CPE
vllm vllm >= 0.5.5, < 0.11.1 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
vllm vllm 0.11.1 cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*
vllm vllm 0.11.1 cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*

References for CVE-2025-62426

cvelogic Threat Intelligence