TI-2026-63191 Aliases CVE-2026-93841 GHSA-q9hm-g73w-q6wp

vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

LOW 28CWE-129Published 2026-09-18 · Updated 2026-09-24

Key facts

Attack vector: Network
Privileges required: None
User interaction: None
Attack complexity: Low
Attack requirements: Present
Impact type: —
Confidentiality · integrity · availability: None · Low · None
Fix status: Deferred Red Hat: fix deferred

Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat.

Summary

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00237 14th percentileScored 2026-11-07

Fix Deferred Red Hat: fix deferred

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	up to 0.29.0	—	No fix listed	CNA

vllm Vendorvllm-project Affected up to 0.29.0 Fixed in — No fix listed CNA

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:vllm:vllm::::::::	up to 0.29.0	Vulnerable	vLLM

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions up to 0.29.0 Vulnerable ·vLLM

Remediation

No fixed version listed by the sources yet.

Vendor assessments

Red Hat

Red Hat rating: Low. 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) 3	Affected	No fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)	Affected	No fix yet: Fix deferred

Timeline

2026-10-02 Threatist record created from CVE-2026-93841
2026-10-03 Alias added: GHSA-q9hm-g73w-q6wp

References

Patch 1

https://github.com/vllm-project/vllm/pull/49081

Other 3

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