CVE-2025-62426

MEDIUM EPSS 23.6%
Published Nov 21, 20257mo ago · Modified Jun 17, 20261w ago
6.5 CVSS 3.1
Medium
Find Similar
Published Nov 21, 2025 7mo ago
Last Modified Jun 17, 2026 1w ago

Description

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.

CVSS Details

Base Score
6.5
Exploitability
2.8
Impact
3.6
Vector string
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Vector Network
Attack Complexity Low
Privileges Required Low
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High

Threat Intelligence

EPSS Exploit Probability
23.6% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 1

CWE-770

Affected Products 3

VendorProductVersionRange
vllmvllm*≥0.5.5  –  <0.11.1
vllmvllm0.11.1any
vllmvllm0.11.1any

References 5

  • github.com https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610
    Product
  • github.com https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814
    Product
  • github.com https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/27205
    Issue Tracking
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p
    Vendor Advisory

Remediation

  • github.com https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b
    Patch