---
cve: "CVE-2026-22778"
severity: "CRITICAL"
cvss: 9.8
epss: "18.5%"
vendor: "vllm-project"
kev: false
exploited: false
published: "2026-02-02 23:16:06"
tags: [cve, security, critical]
source: tsecurity.de CVE-Dossier
exported: "2026-10-31T04:04:04+01:00"
---

# CVE-2026-22778

> 9.8 CRITICAL · 🧪 PoC

## Beschreibung

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

## CNA-Record (Kanon, cvelistV5)

- CNA: **GitHub_M**
- State: PUBLISHED
- Stand: 2026-07-15 01:19:16
- CNA-CVSS: **9.8** (`CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`)

## CISA-Anreicherung (vulnrichment/ADP)

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

## CVSS-Vektor

```
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |
| UI Interaktion | Keine | bad |
| S Scope | Unverändert | good |
| C Vertraulichkeit | Hoch | bad |
| I Integrität | Hoch | bad |
| A Verfügbarkeit | Hoch | bad |

## Schwachstellen-Klasse

- **CWE-209** — Generation of Error Message Containing Sensitive Information
  The product generates an error message that includes sensitive information about its environment, users, or associated data.
- **CWE-532** — Insertion of Sensitive Information into Log File
  The product writes sensitive information to a log file.

## Angriffsmuster (CAPEC)

- [CAPEC-7 — Blind SQL Injection](https://capec.mitre.org/data/definitions/7.html) _(Severity: High)_
- [CAPEC-54 — Query System for Information](https://capec.mitre.org/data/definitions/54.html) _(Severity: Low)_
- [CAPEC-215 — Fuzzing for application mapping](https://capec.mitre.org/data/definitions/215.html) _(Severity: Low)_
- [CAPEC-463 — Padding Oracle Crypto Attack](https://capec.mitre.org/data/definitions/463.html) _(Severity: High)_

## Patch verfügbar (OSV)

- d7de043d55d1dd629554467e23874097e1c48993 (Commit)

## BSI-Hinweise (deutsch)

- [vllm: Schwachstelle ermöglicht Codeausführung](https://wid.cert-bund.de/portal/wid/sicherheitshinweis/WID-SEC-W-2026-0287) — _BSI-Einstufung: hoch_
  Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um beliebigen Programmcode auszuführen.

## Referenzen

- <https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv>
- <https://github.com/vllm-project/vllm/pull/31987>
- <https://github.com/vllm-project/vllm/pull/32319>
- <https://github.com/vllm-project/vllm/releases/tag/v0.14.1>
- <https://access.redhat.com/errata/RHSA-2026:19712>
- <https://access.redhat.com/errata/RHSA-2026:30087>
- <https://access.redhat.com/errata/RHSA-2026:30088>
- <https://access.redhat.com/errata/RHSA-2026:30089>
- <https://access.redhat.com/errata/RHSA-2026:3461>
- <https://access.redhat.com/errata/RHSA-2026:3462>
- <https://access.redhat.com/errata/RHSA-2026:3713>
- <https://access.redhat.com/errata/RHSA-2026:3782>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/sicherheitsluecken/cve-2026-22778/) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI WID (CSAF)_