---
cve: "CVE-2026-73558"
severity: "MEDIUM"
cvss: 5.3
epss: "26%"
vendor: "vllm-project"
kev: false
exploited: false
published: "2026-08-13 15:20:18"
tags: [cve, security, medium]
source: tsecurity.de CVE-Dossier
exported: "2026-09-17T17:41:38+02:00"
---

# CVE-2026-73558

> 5.3 MEDIUM · 🧪 PoC

## Beschreibung

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.

## CVSS-Vektor

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

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

## Patch verfügbar (OSV)

- 451227cb3ff07989698fed982c2d3e4300257924 (Commit)
- 4bdc8a788d2e2ce9165d552b3d4d8b72604626bf (Commit)

## Referenzen

- <https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5>
- <https://github.com/vllm-project/vllm/issues/42860>
- <https://github.com/vllm-project/vllm/pull/49660>
- <https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924>
- <https://github.com/vllm-project/vllm/releases/tag/v0.27.0>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-73558) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_