TI-2026-80199 Aliases CVE-2026-116181 GHSA-f2x4-7hx3-gxfp

Denial of service and out-of-bounds write in vLLM via stop_token_ids

LOW 31CWE-129Published 2026-10-25 · Updated 2026-10-29

Key facts

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

Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat. Impact type from CWE-129 and the CVSS impact.

Summary

vLLM from 0.20.1 before 0.29.0 fails to validate stop_token_ids, so out-of-vocabulary IDs are accepted (CWE-129). A remote attacker with low privileges can send chat, completion, generate, or batch requests with invalid IDs to crash the engine or write outside the V2 runner's logits buffer.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

Description from the CNA

vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00374 31st percentileScored 2026-11-07

Fix Partial vllm (vllm-project): 0.29.0Red Hat: 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	0.20.1 to before 0.29.0	0.29.0	Patch available	CNA

vllm Vendorvllm-project Affected 0.20.1 to before 0.29.0 Fixed in 0.29.0 Patch available CNA

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:vllm:vllm::::::::	0.20.1 to before 0.29.0	Vulnerable	vLLM

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.20.1 to before 0.29.0 Vulnerable ·vLLM

Remediation

Upgrade vllm to version 0.29.0, which fixes the flaw. Red Hat lists no available plan for Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, and Red Hat OpenShift AI (RHOAI).

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

Fix · CNA vllm (vllm-project) Fixed in 0.29.0

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

Timeline

2026-10-25 Threatist record created from CVE-2026-116181
2026-10-25 Affected versions changed · Red Hat
2026-10-25 CVSS score added · Red Hat
2026-10-26 Priority changed: MEDIUM → LOW
2026-10-27 Alias added: GHSA-f2x4-7hx3-gxfp
2026-10-29 CISA SSVC decision points changed

References

Patch 1

GitHub Security Advisory (GHSA-w9r6-29q4-pvpr)

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