DeutschShown in its original language — a full translation is planned for a future version.
vllm: Mehrere Schwachstellen ermöglichen Denial of Service
view advisory published 2026-07-01
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.
01
describes (4)
Related CVEs.
| ID | severity | exploitable | ||
|---|---|---|---|---|
| CVE-2026-55574US | high7.5 | — | ||
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular exp… | ||||
| CVE-2026-55514US | medium6.5 | — | ||
vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes En… | ||||
| CVE-2026-54234US | — | — | ||
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the re… | ||||
| CVE-2026-55646US | — | — | ||
vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to… | ||||
02
references
External citations — patches, advisories, analysis.
- Red Hat Security Advisory RHSA-2026:60363 vom 2026-08-26external
- Red Hat Security Advisory RHSA-2026:61627 vom 2026-08-31external
- Red Hat Security Advisory RHSA-2026:61629 vom 2026-08-31external
- Red Hat Security Advisory RHSA-2026:70965 vom 2026-09-23external
- Red Hat Security Advisory RHSA-2026:70969 vom 2026-09-23external
- Red Hat Security Advisory RHSA-2026:70979 vom 2026-09-23external
- Red Hat Security Advisory RHSA-2026:70995 vom 2026-09-23external
- Red Hat Security Advisory RHSA-2026:76149 vom 2026-10-05external
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