---
cve: "CVE-2026-100651"
severity: "HIGH"
cvss: 7.1
epss: ""
vendor: "vllm-project"
kev: false
exploited: false
published: "2026-09-26 14:16:47"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-27T16:58:26+02:00"
---

# CVE-2026-100651

> 7.1 HIGH · 🧪 PoC

## Beschreibung

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.

## CNA-Record (Kanon, cvelistV5)

- CNA: **VulnCheck**
- State: PUBLISHED
- Stand: 2026-09-26 13:23:21
- CNA-CVSS: **7.1** (`CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N`)

## CVSS-Vektor

```
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Gering | warn |
| UI Interaktion | Keine | bad |

## Patch verfügbar (OSV)

- 98dff2a81d747d1dba01a47f939f48c3526d4206 (Commit)

## Referenzen

- <https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9>
- <https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-decoder-prompt-length-bypass>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-100651) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI WID (CSAF)_