Threat landscape
high

vllm: Schwachstelle ermöglicht Umgehen von Sicherheitsvorkehrungen

WID-SEC-2026-1974 · first 17.06.2026 · updated 06.10.2026 · CVSS 9,1

×

What it is about

Open Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs). Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um Sicherheitsvorkehrungen zu umgehen.

Under what conditions?

Over the network and without logging in. This is the most dangerous combination: attackers can scan reachable devices automatically.

What can happen in the worst case

An attacker could use the vulnerability to

  • Sicherheitsvorkehrungen zu umgehen

Am I affected?

Affected according to the BSI:

  • Red Hat Enterprise Linux
  • Open Source vllm <0.22.0

The installed version is usually shown under “Help → About” or in the device’s admin interface.

What helps?

Update to at least:

  • Open Source vllm 0.22.0

Is the vulnerability already being exploited?

None of the CVEs is in the CISA catalogue of exploited vulnerabilities. That does not mean there are no attacks, only that none are documented.

Information and sources

CVE: CVE-2026-48746

Source: BSI warning and information service (CERT-Bund); CISA. The assessment of the conditions is my reading of the BSI text; the external pages are in their original language.

Set up in an hour, trained in a week.

Create a free account, add your team, unlock the course. You only pay when you start. Would you rather see what a test email looks like first? The self-test is free.

Add your team Test it yourself first