Skip to content
OpenAdvisories
High WID-SEC-2026-4076 7 CVEs

vllm: Mehrere Schwachstellen

Published Oct 20, 2026 · Updated Nov 12, 2026 · Revision 4 · de

Vendor: Red Hat Product: Enterprise Linux Platform: Linux

Summary

Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Daten zu manipulieren, einen Denial-of-Service-Angriff durchzuführen oder beliebigen Programmcode auszuführen.

Product

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

Vulnerabilities 7

  • High 8.1
    CVE-2026-114053

    vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision

    vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust_remote_code is enable…

    vLLM vLLM vllm PyPI
  • High 7.5
    CVE-2026-114050

    vLLM before 0.31.0 Remote Engine Crash via Forged Multimodal UUID

    vLLM before 0.31.0 uses a client-supplied multimodal uuid verbatim as cache identity with no consistency check on cache hits, allowing engine crashes. Unauthenticated attackers can desynchronize the P0/P1 processor caches to trigger a fatal token-placeholder …

    vLLM vLLM vllm PyPI
  • High 7.5
    CVE-2026-114051

    vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate

    vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attack…

    vLLM vLLM
  • High 7.5
    CVE-2026-114052

    vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs

    vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can send d…

    vLLM vLLM vllm PyPI
  • High 7.5
    CVE-2026-114055

    vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs

    vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters by supplying per-request mm_processor_kwargs. Attackers can set large image size, patch count, crop…

    vLLM vLLM vllm PyPI
  • Medium 6.5
    CVE-2026-114054

    vLLM before 0.31.0 Cross-Request Cache Aliasing via EXIF ImageID and Prefix-Cache Keys

    vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled values such as EXIF ImageID or cache_salt. Attackers can set a UUID EXIF ImageID to receive another requ…

    vLLM vLLM vllm PyPI
  • Low 3.7
    CVE-2026-114049

    vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense

    vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including v…

    vLLM vLLM

Revision history

  1. #4

    Neue Updates von Red Hat aufgenommen

  2. #3

    Neue Updates von Red Hat aufgenommen

  3. #2

    Neue Updates von Red Hat aufgenommen

  4. #1

    Initiale Fassung

References