What it is about

Open Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs). Ein entfernter, authentisierter Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen und um Informationen offenzulegen.

Under what conditions?

Over the network, but only with valid access (login required), for example with stolen credentials or as an insider.

What can happen in the worst case

An attacker could use the vulnerability to

• einen Denial of Service Angriff durchzuführen
• Informationen offenzulegen

Am I affected?

Affected according to the BSI:

• Open Source vllm <0.18.0
• Open Source vllm <0.24.0
• Open Source vllm <0.29.0
• Open Source vllm <0.30.0
• Open Source vllm <0.25.0
• Open Source vllm <0.31.0

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 0.18.0
• Open Source vllm 0.24.0
• Open Source vllm 0.29.0
• Open Source vllm 0.30.0
• Open Source vllm 0.25.0
• Open Source vllm 0.31.0

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.