---
cve: "CVE-2026-100654"
severity: "HIGH"
cvss: 7.1
epss: "0.3%"
vendor: "vllm-project"
kev: false
exploited: false
published: "2026-09-26 14:16:48"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-30T08:46:46+02:00"
---

# CVE-2026-100654

> 7.1 HIGH · 🧪 PoC

## Beschreibung

vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).

## CNA-Record (Kanon, cvelistV5)

- CNA: **VulnCheck**
- State: PUBLISHED
- Stand: 2026-09-26 13:23:23
- 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)

## BSI-Hinweise (deutsch)

- [vllm: Mehrere Schwachstellen ermöglichen](https://wid.cert-bund.de/portal/wid/sicherheitshinweis/WID-SEC-W-2026-3327) — _BSI-Einstufung: mittel_
  Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Sicherheitsvorkehrungen zu umgehen, Daten zu manipulieren, sensible Informationen offenzulegen oder einen Denial-of-Service-Zustand auszulösen.

## Referenzen

- <https://github.com/vllm-project/vllm/security/advisories/GHSA-v5gm-qgmv-gc6c>
- <https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-out-of-range-stop-token-ids>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-100654) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI WID (CSAF)_