DeutschShown in its original language — a full translation is planned for a future version.
vllm: Mehrere Schwachstellen
view advisory published 2026-08-10
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Informationen offenzulegen, und um einen Denial of Service Angriff durchzuführen.
01
describes (2)
Related CVEs.
| ID | severity | exploitable | ||
|---|---|---|---|---|
| CVE-2026-78684US | medium5.3 | — | ||
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… | ||||
| CVE-2026-73558US | — | — | ||
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… | ||||
02
references
External citations — patches, advisories, analysis.
scry
Advisories like this name the exposed products attackers go after on your perimeter. See what is exposed on your perimeter with a free passive scan.
Free scan