Skip to content
OpenAdvisories
Medium WID-SEC-2026-1897 5 CVEs

vllm: Mehrere Schwachstellen

Published Jun 11, 2026 · Updated Oct 5, 2026 · Revision 10 · de-DE

Vendor: Red Hat Product: Enterprise Linux Platform: Linux

Summary

Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Sicherheitsmaßnahmen zu umgehen, einen Denial-of-Service-Zustand zu verursachen, Daten zu manipulieren oder vertrauliche Informationen offenzulegen.

Product

Open Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs).

Vulnerabilities 5

  • High 7.5
    CVE-2026-5497

    Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

    vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data…

    vLLM vllm-project/vllm vllm PyPI
  • Medium 6.9
    CVE-2026-54235

    vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

    vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semant…

    vLLM vLLM vllm PyPI
  • Medium 6.5
    CVE-2026-54233

    vLLM: OOM Denial of Service via Audio Decompression Bomb

    vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time.…

    vLLM vLLM vllm PyPI
  • Medium 5.3
    CVE-2026-53923

    vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow

    vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The outpu…

    vLLM vLLM vllm PyPI
  • Medium 5.3
    CVE-2026-54236 Scanner template

    vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router

    vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is …

    vLLM vLLM vllm PyPI

Revision history

  1. #10

    Neue Updates von Red Hat aufgenommen

  2. #9

    Neue Updates von Red Hat aufgenommen

  3. #8

    Neue Updates von Red Hat aufgenommen

  4. #7

    Neue Updates von Red Hat aufgenommen

  5. #6

    Neue Updates von Red Hat aufgenommen

  6. #5

    Neue Updates von Red Hat aufgenommen

  7. #4

    Neue Updates von Red Hat aufgenommen

  8. #3

    Neue Updates von Red Hat aufgenommen

  9. #2

    Referenz(en) aufgenommen: CVE-2026-54233, EUVD-2026-38404, CVE-2026-54235, EUVD-2026-38402, CVE-2026-53923, EUVD-2026-38400, CVE-2026-54236, EUVD-2026-38403

  10. #1

    Initiale Fassung

References