TI-2026-32201 Aliases CVE-2026-44222 GHSA-hpv8-x276-m59f

vLLM: Remote DoS via Special-Token Placeholders

LOW 33CWE-129Published 2026-05-12 · Updated 2026-05-13

Key facts

Attack vector: Network
Privileges required: None
User interaction: None
Attack complexity: Low
Impact type: Denial of service
Confidentiality · integrity · availability: None · None · High
Fix status: Partial Red Hat: 2 fixed, 3 without a fix

Attack profile from CVSS 3.1 · NVD. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-129 and the CVSS impact.

Summary

vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00414 35th percentileScored 2026-11-07

Public exploit Yes 1 exploit referenceTagged by NVD

Fix Partial vllm (vllm-project): 0.20.0vllm (PyPI): 0.20.0Red Hat: 3 advisoriesRed Hat: 2 fixed, 3 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	0.6.1 to before 0.20.0	0.20.0	Patch available	CNA
—	vllm (PyPI)	0.6.1 to before 0.20.0	0.20.0	Patch available	GHSA-hpv8-x276-m59f

vllm Vendorvllm-project Affected 0.6.1 to before 0.20.0 Fixed in 0.20.0 Patch available CNA
vllm (PyPI) Vendor— Affected 0.6.1 to before 0.20.0 Fixed in 0.20.0 Patch available GHSA-hpv8-x276-m59f

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:vllm:vllm::::::::	0.6.1 to before 0.20.0	Vulnerable	vLLM

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.6.1 to before 0.20.0 Vulnerable ·vLLM

Remediation

Fix · CNA vllm (vllm-project) Fixed in 0.20.0
Fix · GHSA-hpv8-x276-m59f vllm (PyPI) Fixed in 0.20.0 Advisory →

Red Hat 3 advisories

RHSA-2026:61629 Released 2026-08-31 · Red Hat rating Important
Red Hat AI Inference Server 3.2.2 (ROCm)
- Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-rocm-rhel9
RHSA-2026:61627 Released 2026-08-31 · Red Hat rating Important
Red Hat AI Inference Server 3.2.2 (CUDA)
- Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-cuda-rhel9
RHSA-2026:60363 Released 2026-08-26 · Red Hat rating Important
Red Hat AI Inference Server 3.3.6 (Spyre)
- Red Hat AI Inference Server 3.3 registry.redhat.io/rhaiis/vllm-spyre-rhel9

Vendor assessments

Red Hat

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

Product	Status	Plan or fix
Red Hat AI Inference Server	Affected	No fix planned: Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3	Affected	No fix yet
Red Hat OpenShift AI (RHOAI)	Affected	No fix yet
Red Hat AI Inference Server 3.2	Fixed	RHSA-2026:61627, RHSA-2026:61629
Red Hat AI Inference Server 3.3	Fixed	RHSA-2026:60363

Not affected: 1 product

Red Hat OpenShift AI (RHOAI)

Timeline

2026-10-02 Threatist record created from CVE-2026-44222
2026-10-03 Alias added: GHSA-hpv8-x276-m59f

References

Exploit 1

https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f

Advisory 2

Other 4

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