Home/CVE/vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/c
CVE

CVE-2025-62426

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/c

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.

MEDIUM · CVSS 6.5 EPSS 0.00089
Monitor
  • No active-exploitation, high-EPSS, or public-exploit signals - routine patching cadence
Sigma rules0 YARA rules0
⬡

Weakness Classification

CWE-770Allocation of Resources Without Limits or Throttling
▤

Affected Products & Versions

2
vllm>= 0.5.5 and < 0.11.1
vllmall versions
▤

Affected Packages

1
Language-ecosystem packages (from OSV) tied to this CVE, with the version that fixes it - the dependency-level detail NVD doesn’t carry.
PyPI vllm MODERATE fixed in 0.11.1
▣

Scoring & Timeline

6.5
MEDIUM · CVSS v3.1 · security-advisories@github.com
View on NVD
Attack Vector
Network Adjacent Local Physical
Attack Complexity
Low High
Privileges Required
None Low High
User Interaction
None Required
Scope
Unchanged Changed
Confidentiality
None Low High
Integrity
None Low High
Availability
None Low High
Published to NVD21 Nov 2025 · 02:15 AM
CVSS VectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
SSVC triage · cisa-vulnrichment
Exploitation
none
Automatable
no
Technical impact
partial
SSVC asks the questions that actually drive patch urgency: is it being exploited, can attacks be automated, and how total is the impact.
⚑

Vendor Advisories

2
rhsaRHSA-2026:3462Important
rhsaRHSA-2026:3461Important
🔗

References & Sources

5
Source URLs (vendor pages, mailing lists, write-ups). Exploit/PoC links are in their own section above to avoid duplication.
https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610Product
https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814Product
https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2bPatch
https://github.com/vllm-project/vllm/pull/27205Issue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64pVendor Advisory
Intelligence Graph · click any node to traverse
CVETechnique ActorTool Family
drag to reposition · click any node to traverse · button top-right enlarges
External lookups - second-class, for what we don’t hold ourselves
NVDCVE.orgCISAVulnersExploit-DBGitHub PoCVulnCheck KEVGreyNoise
Vulnerabilities
CISA KEV catalog
CWE weaknesses
CAPEC attack patterns
Package vulnerabilities
Threat intelligence
Threat actors
Tools & malware
ATT&CK techniques
IOCs
Detection & defense
Sigma rules
YARA rules
Atomic Red Team tests
D3FEND countermeasures
Compliance
NIST 800-53
ISO 27001:2022
SOC 2 TSC
PCI-DSS v4.0
CIS Controls v8.1
About
All capabilities
Live statistics
Data sources
Privacy policy
Terms of service
threatengine.sh  ·  Open-source threat intelligence platform  ·  100+ authoritative sources  ·  Every fact traces to its origin