CVE Feed

    Dashboard / CVE / CVE-2026-90555

    CVE-2026-90555

    vLLM versions before 0.28.0 fail to validate audio sample rate headers in the transcription endpoint, allowing authenticated clients to bypass duration checks. Attackers can submit forged FLAC headers with inflated sample rates to trigger excessive memory allocation and crash the API server process affecting all tenants.

    Published:Sep 12, 2026
    Last Modified:Sep 12, 2026
    EPS:Sep 12, 2026
    EPSS Score:
    CVSS Score:6.5

    Affected Products

    Vendor
    Vllm
    Product
    Vllm

    Exploits

    No exploit reference

    Common Attack Pattern Enumeration and Classification (CAPEC)

    No CAPEC recorded yet

    Related CVEs

    CVE-2026-90554 (CVSS 6.9) — vLLM versions >=0.10.2 and <0.28.0 do not apply any audio decode-size or duration limit when extracting audio …
    CVE-2026-90553 (CVSS 8.5) — vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that…
    CVE-2026-78684 (CVSS 6.9) — vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in…
    CVE-2026-41523 (CVSS 7.5) — vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based sec…
    CVE-2026-48746 (CVSS 9.1) — vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerabi…
    CVE-2026-56340 (CVSS 8.7) — vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing.…
    CVE-2025-71379 (CVSS 5.3) — vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabiliti…
    CVE-2026-5497 (CVSS 7.5) — vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to u…
    CVE-2026-44223 (CVSS 6.5) — vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the ex…
    CVE-2026-44222 (CVSS 6.5) — vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there i…

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High
    CVE-2026-90555 — Vllm (High 7.1) | CVE-DB