TI-2026-64811 Aliases CVE-2026-100651 GHSA-g43f-v3gj-45x5

vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass

MEDIUM 64CWE-400Published 2026-09-26 · Updated 2026-09-28

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-400.

Summary

vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len. For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV

EPSS 0.00384 32nd percentileScored 2026-11-07

Public exploit Yes 1 exploit referenceTagged by NVD

Fix Partial vllm (vllm-project): 0.29.0Red Hat: 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation: Poc
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	before 0.29.0	0.29.0	Patch available	CNA

vllm Vendorvllm-project Affected 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::::::::	before 0.29.0	Vulnerable	vLLM

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

Remediation

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

Fixed in the same release

Records fixed by the same vendor advisory or release, as the CNA lists them.

Release · 2026-09-26
vllm-project vllm 0.29.0
6 records Highest priority Priority MEDIUM 2 MEDIUM, 4 LOW
Other records, highest priority first
- TI-2026-64810 vLLM before 0.29.0 Resource Exhaustion via Unbounded Media MaterializationPriority MEDIUM 64
- TI-2026-64808 vllm before 0.29.0 Uncontrolled Resource Consumption via Audio DecodingPriority LOW 36
- TI-2026-64807 vLLM before 0.29.0 CPU Exhaustion via unbounded cache_saltPriority LOW 36
Show all 6 records →

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

2026-10-02 Threatist record created from CVE-2026-100651
2026-10-03 Alias added: GHSA-g43f-v3gj-45x5

References

Exploit 1

GitHub Security Advisory (GHSA-3mqx-f33v-vgp9)

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