---
cve: "CVE-2026-78684"
severity: "MEDIUM"
cvss: 6.9
epss: "0.6%"
vendor: "vllm-project"
kev: false
exploited: false
published: "2026-08-25 11:33:22"
tags: [cve, security, medium]
source: tsecurity.de CVE-Dossier
exported: "2026-10-01T13:44:05+02:00"
---

# CVE-2026-78684

> 6.9 MEDIUM · 🧪 PoC

## Beschreibung

vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causing partial denial of service for concurrent requests.

## CISA-Anreicherung (vulnrichment/ADP)

- CISA-SSVC (Coordinator, v2.0.3):
  - Exploitation: **none**
  - Automatable: **yes**
  - Technical Impact: **partial**

## CVSS-Vektor

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

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

## Patch verfügbar (OSV)

- 4bdc8a788d2e2ce9165d552b3d4d8b72604626bf (Commit)
- e23b19309b8705b21c3b3ff4129c9974ba15a419 (Commit)

## BSI-Hinweise (deutsch)

- [vllm: Mehrere Schwachstellen](https://wid.cert-bund.de/portal/wid/sicherheitshinweis/WID-SEC-W-2026-2739) — _BSI-Einstufung: mittel_
  Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Informationen offenzulegen, und um einen Denial of Service Angriff durchzuführen.

## Referenzen

- <https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq>
- <https://github.com/vllm-project/vllm/commit/e23b19309b8705b21c3b3ff4129c9974ba15a419>
- <https://www.vulncheck.com/advisories/vllm-before-denial-of-service-via-deepstream-backend>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-78684) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI WID (CSAF)_