TI-2025-38693 Aliases CVE-2025-62426 GHSA-69j4-grxj-j64p

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

LOW 30CWE-770Published 2025-11-21 · Updated 2025-11-24

Key facts

Attack vector: Network
Privileges required: Low
User interaction: None
Attack complexity: Low
Impact type: Denial of service
Confidentiality · integrity · availability: None · None · High
Fix status: Partial Red Hat: 1 fixed, 4 without a fix

Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-770.

Summary

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00538 45th percentileScored 2026-11-07

Fix Partial vllm (vllm-project): 0.11.1vllm (PyPI): 0.11.1Red Hat: 2 advisoriesRed Hat: 1 fixed, 4 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation: None
Automatable: No
Technical impact: Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

Vendor	Product	Affected versions	Fixed in	Status	Source
vllm-project	vllm	0.5.5 to before 0.11.1	0.11.1	Patch available	CNA
—	vllm (PyPI)	0.5.5 to before 0.11.1	0.11.1	Patch available	GHSA-69j4-grxj-j64p

vllm Vendorvllm-project Affected 0.5.5 to before 0.11.1 Fixed in 0.11.1 Patch available CNA
vllm (PyPI) Vendor— Affected 0.5.5 to before 0.11.1 Fixed in 0.11.1 Patch available GHSA-69j4-grxj-j64p

CPE configurations NVD · 3

CPE	Versions	Role	Vendor
cpe:2.3:a:vllm:vllm::::::::	0.5.5 to before 0.11.1	Vulnerable	vLLM
cpe:2.3:a:vllm:vllm:0.11.1:rc0::::::	0.11.1 rc0	Vulnerable	vLLM
cpe:2.3:a:vllm:vllm:0.11.1:rc1::::::	0.11.1 rc1	Vulnerable	vLLM

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.5.5 to before 0.11.1 Vulnerable ·vLLM
cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:* Versions 0.11.1 rc0 Vulnerable ·vLLM
cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:* Versions 0.11.1 rc1 Vulnerable ·vLLM

Remediation

Fix · CNA vllm (vllm-project) Fixed in 0.11.1
Fix · GHSA-69j4-grxj-j64p vllm (PyPI) Fixed in 0.11.1 Advisory →

Red Hat 2 advisories

RHSA-2026:3462 Released 2026-02-27 · Red Hat rating Critical
Red Hat AI Inference Server 3.2.2 (ROCm)
- Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-rocm-rhel9
RHSA-2026:3461 Released 2026-02-27 · Red Hat rating Critical
Red Hat AI Inference Server 3.2.2 (CUDA)
- Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-cuda-rhel9

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

Product	Status	Plan or fix
Red Hat AI Inference Server	Affected	No fix yet: Fix deferred
Red Hat Enterprise Linux AI (RHEL AI)	Affected	No fix yet: Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3	Affected	No fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)	Affected	No fix yet: Fix deferred
Red Hat AI Inference Server 3.2	Fixed	RHSA-2026:3461, RHSA-2026:3462

Timeline

2026-10-02 Threatist record created from CVE-2025-62426
2026-10-03 Alias added: GHSA-69j4-grxj-j64p

References

Patch 1

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

Advisory 3

Other 6

TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5

See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences