CVE Feed

    Dashboard / CVE / CVE-2026-93592

    CVE-2026-93592

    vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that poisons the GPU context, causing all subsequent requests to fail until the process restarts.

    Published:Sep 18, 2026
    Last Modified:Sep 22, 2026
    EPS:Sep 18, 2026
    EPSS Score:0.00377
    CVSS Score:7.5

    Affected Products

    Vendor
    Vllm
    Product
    Vllm

    Exploits

    https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpfhttps://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf

    Common Attack Pattern Enumeration and Classification (CAPEC)

    CAPEC-100 Overflow Buffers

    Related CVEs

    CVE-2026-115918 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses…
    CVE-2026-115917 (CVSS 3.4) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible serv…
    CVE-2026-115916 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py comp…
    CVE-2026-115915 (CVSS 8.1) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attack…
    CVE-2026-115914 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR,…
    CVE-2026-115913 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio…
    CVE-2026-115912 (CVSS 7.5) — vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller ca…
    CVE-2026-115911 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated cal…
    CVE-2026-116180 (CVSS 8.3) — vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py …
    CVE-2026-116181 (CVSS 7.1) — vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attacker…

    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