HighCVE-2026-116172

    vllm: Improper Input Validation (CVE-2026-116172)

    Published Last modified Sources: BSI

    Share

    What is affected, what to do

    vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC converter that allows remote attackers to bypass max_logprobs limits via CandidateTokens.top_n. Attackers can send Generate or GenerateStream requests with oversized or integer-wrapping top_n values to trigger torch.topk failures that terminate EngineCore.

    Update vLLM to version 0.24.0.

    Affected
    • vLLM lt 0.22.0..0.24.0
    Fixed in
    • vLLM 0.24.0

    Not sure whether and how you are affected? Ask a question about this vulnerability

    Metrics

    8.2

    Priority

    XIEM Effective CVSS: highest available CVSS rating from NVD and vendor data.

    Source: Vendor (CNA), CVSS v4

    7.5

    CVSS v3

    Severity High on the scale from 0 to 10.

    Source: BSI

    0.3 %

    EPSS score

    Low — model estimates < 1% exploitation likelihood.

    Source: FIRST EPSS, percentile 27.4

    Show all metrics
    Severity
    High
    Priority (0–325)

    The priority score is a consolidated metric that condenses several individual signals into a single, action-guiding ranking: technical severity (CVSS), exploitation likelihood (EPSS), known-exploited status (KEV) and the context of the affected asset. The aim is to answer the only truly important question in vulnerability management: what first?

    Read in glossary
    76.57 Methodology
    Exploit maturity

    An exploit is code or a technique that specifically uses a concrete vulnerability to force unintended behaviour — such as executing code or escalating privileges. It is the tool that turns a theoretical flaw into a practical attack.

    Read in glossary
    no public PoC known
    XIEM Effective CVSS

    XIEM® is the tiered managed-security operating model from NEOSEC and a registered trademark of NEOSEC GmbH. It extends classic SIEM — the central collection, normalisation and correlation of security-relevant events — with endpoint forensics, network visibility and deception technology, and consolidates them into three building tiers: Sentry, Orchestrate and Command.

    Read in glossary
    8.2 Methodology
    CVSS v3

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    7.5
    CVSS v4

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    8.2
    EPSS score

    The EPSS score is the absolute model output for an individual vulnerability: the estimated probability of real-world exploitation within the next 30 days, expressed as a value between 0 and 1 (i.e. 0 % to 100 %). A score of 0.42 means „the model estimates a 42 % chance of real-world exploitation within 30 days“.

    Read in glossary
    0.3 %
    Low — model estimates < 1% exploitation likelihood.
    EPSS percentile

    The EPSS percentile is the relative position of a vulnerability within all EPSS-scored CVEs, expressed as a value between 0 and 1. A percentile of 0.90 means „this CVE has a higher EPSS score than 90 % of all other scored CVEs“. Unlike the EPSS score, it is not a probability — but a positioning within a ranking.

    Read in glossary
    27.4
    Elevated — this CVE ranks above at least 10% of all CVEs scored today.
    KEV status

    The KEV catalogue is a list maintained by the US authority CISA of vulnerabilities for which active exploitation in the wild has been confirmed. It answers not the question „how severe?“ but „is it already being attacked?“ — thereby sharply prioritising patching.

    Read in glossary
    —
    Published
    CWE

    CWE is a catalogue of typical weakness types in software and hardware — such as flawed input validation, unsafe memory handling or poor authentication. Where a CVE names a concrete vulnerability in a concrete product, a CWE describes the underlying class of defect.

    Read in glossary
    CWE-20

    Detection rules

    No NEOSEC detection rule is available for this vulnerability yet.

    Classification under NIS2 and CRA

    Rule-based classification from exploitation status and severity. It does not replace a case-by-case assessment.

    NIS2

    NIS2 is EU Directive (EU) 2022/2555 to raise the level of cybersecurity across the Union. It substantially broadens obligations compared with the first NIS directive: more sectors, mandatory risk management, staged reporting duties and personal accountability of senior management.

    Read in glossary
    High technical severity: assess and remediate the vulnerability in vulnerability handling under Art. 21(2)(e) NIS2 and document the decision.
    CRA

    The CRA is EU Regulation (EU) 2024/2847 setting horizontal cybersecurity requirements for „products with digital elements“ — from industrial controllers and software to connected consumer devices. For the first time manufacturers must ensure security across the entire product lifecycle, handle vulnerabilities and provide security updates.

    Read in glossary
    From 11.12.2027, Annex I Part II CRA requires manufacturers of affected products with digital elements to handle vulnerabilities without delay and provide security updates.
    ISO/IEC 27001

    ISO/IEC 27001 is the internationally leading standard for an information security management system (ISMS). It describes a risk-based, process-oriented framework to systematically plan, implement, review and improve information security.

    Read in glossary
    Control A.8.8, management of technical vulnerabilities: assess relevance to your systems, plan remediation and keep evidence.

    Description

    vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC converter that allows remote attackers to bypass max_logprobs limits via CandidateTokens.top_n. Attackers can send Generate or GenerateStream requests with oversized or integer-wrapping top_n values to trigger torch.topk failures that terminate EngineCore.

    Source: BSI WID Portal

    Affected products

    The following versions are affected. Older releases of the same product line are also vulnerable unless stated otherwise.

    Affected products
    Affected versionsFixed in
    vllm-projectvllm
    • 0.10.2 – < 0.25.0
    • 0.18.0 – < 0.31.0
    • 0.20.0 – < 0.30.0
    • 0.22.0 – < 0.24.0
    • 0.8.5 – < 0.31.0
    • 0.9.2 – < 0.24.0
    • 0.25.0
    • 0.31.0
    • 0.30.0
    • 0.24.0
    • 0.31.0
    • 0.24.0
    vllmvllm
    • 0.10.2 – < 0.25.0
    • 0.18.0 – < 0.31.0
    • 0.20.0 – < 0.30.0
    • 0.22.0 – < 0.24.0
    • 0.8.5 – < 0.31.0
    • 0.9.2 – < 0.24.0
    • 0.25.0
    • 0.31.0
    • 0.30.0
    • 0.24.0
    • 0.31.0
    • 0.24.0
    Open Sourcevllm
    • < 0.18.0
    • < 0.24.0
    • < 0.25.0
    • < 0.29.0
    • < 0.30.0
    • < 0.31.0
    • 0.18.0
    • 0.24.0
    • 0.25.0
    • 0.29.0
    • 0.30.0
    • 0.31.0
    pypivllm
    • 0.10.0
    • 0.10.1
    • 0.10.1.1
    • 0.10.2
    • 0.11.0
    • 0.11.1
    • 0.11.2
    • 0.12.0
    • 0.13.0
    • 0.14.0
    • 0.14.1
    • 0.15.0
    • 0.15.1
    • 0.16.0
    • 0.17.0
    • 0.17.1
    • 0.18.0
    • 0.18.1
    • 0.19.0
    • 0.19.1
    • 0.20.0
    • 0.20.1
    • 0.20.2
    • 0.21.0
    • 0.22.0
    • 0.22.1
    • 0.23.0
    • 0.24.0
    • 0.25.0
    • 0.25.1
    • —
    • —
    • —
    • 0.25.0
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • 0.30.0
    • —
    • —
    • —
    • 0.24.0
    • —
    • —
    • —
    • —
    • —

    Vendors and products

    Weakness classes (CWE)

    • CWE-20Improper Input Validation

      Class

      The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.

      Entry at MITRE CWE-20

    References & sources

    • github.comGitHub Security Advisory (GHSA-rwfw-xvg3-3937)Vendor advisory, Mitigation, Vendor advisory
    • vulncheck.comVulnCheck Advisory: vLLM 0.22.0 before 0.24.0 DoS via Rust gRPC CandidateTokens.top_nThird-party advisory, Third-party advisory
    • github.comGitHub Security Advisory (GHSA-vfp2-c8pq-v6h6)Vendor advisory, Vendor advisory, advisory
    • vulncheck.comVulnCheck Advisory: vLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnectorThird-party advisory, Third-party advisory, advisory
    • github.comGitHub Security Advisory (GHSA-34qw-q2h2-jp3m)Vendor advisory, Patch, Vendor advisory, fix
    • vulncheck.comVulnCheck Advisory: vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholdersThird-party advisory, Third-party advisory, advisory
    • github.comGitHub Security Advisory (GHSA-rhcx-5729-88vg)Vendor advisory, Mitigation, Vendor advisory
    • vulncheck.comVulnCheck Advisory: vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensorsThird-party advisory, Third-party advisory
    • github.comGitHub Security Advisory (GHSA-mm38-5g96-7j6x)Vendor advisory, Patch, Vendor advisory, fix
    • vulncheck.comVulnCheck Advisory: vLLM 0.10.2 before 0.25.0 DoS via Nemotron-VL Processor Decompression-Bomb Guard BypassThird-party advisory, Third-party advisory, advisory
    • github.comGitHub Security Advisory (GHSA-6pgw-f3pv-4h8q)Vendor advisory, Mitigation, Vendor advisory, advisory
    • vulncheck.comVulnCheck Advisory: vLLM 0.22.0 before 0.24.0 Denial of Service via gRPC output_candidates.token_idsThird-party advisory, Third-party advisory, advisory
    • github.comGitHub Security Advisory (GHSA-4m6g-h9mv-wqjc)Vendor advisory, Patch, Vendor advisory
    • vulncheck.comVulnCheck Advisory: vLLM 0.18.0 before 0.31.0 Memory Exhaustion via media_io_kwargs num_frames OverrideThird-party advisory, Third-party advisory

    Changes to this CVE

    Who changed this CVE and when: NVD (analysis, affected products, CVSS), the CVE publisher (CNA) and additional providers such as CISA (ADP).

    1. Initial analysis by NVDNVD

      Newly listed as affected:
      • vLLM (0.22.0 – before 0.24.0)

      CVSS V3.1: AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

      Show 4 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      CVSSadded
      —
      AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
      Product configurationadded
      —
      OR *cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* versions from (including) 0.22.0 up to (excluding) 0.24.0
      Reference typeadded
      —
      VulnCheck: https://github.com/vllm-project/vllm/security/advisories/GHSA-rwfw-xvg3-3937 Types: Mitigation, Vendor Advisory
      Reference typeadded
      —
      VulnCheck: https://www.vulncheck.com/advisories/vllm-0.22.0-before-0.24.0-dos-via-rust-grpc-candidatetokens-top-n Types: Third Party Advisory

      Source identifier: nvd@nist.gov

    2. ReceivedVulnCheck

      CVSS V4.0: AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

      CVSS V3.1: AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H

      Weakness type: CWE-20

      Description added or changed

      Show 7 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      Descriptionadded
      —
      vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC converter that allows remote attackers to bypass max_logprobs limits via CandidateTokens.top_n. Attackers can send Generate or GenerateStream requests with oversized or integer-wrapping top_n values to trigger torch.topk failures that terminate EngineCore.
      CVSSadded
      —
      AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
      CVSSadded
      —
      AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
      Weakness type (CWE)added
      —
      CWE-20
      Affected versions (publisher)added
      —
      New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/116xxx/CVE-2026-116172.json">CVE-2026-116172</a>
      Referenceadded
      —
      https://github.com/vllm-project/vllm/security/advisories/GHSA-rwfw-xvg3-3937
      Referenceadded
      —
      https://www.vulncheck.com/advisories/vllm-0.22.0-before-0.24.0-dos-via-rust-grpc-candidatetokens-top-n

      Source identifier: disclosure@vulncheck.com

    Linked CVEs

    Linked CVEs
    HighCVE-2026-116180vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensors7.7—
    HighCVE-2026-116179vLLM 0.18.0 before 0.31.0 Memory Exhaustion via media_io_kwargs num_frames Override7.5—
    HighCVE-2026-116178vLLM 0.20.0 before 0.30.0 DoS via /inference/v1/generate mm_placeholders7.5—
    HighCVE-2026-116177vLLM 0.10.2 before 0.25.0 DoS via Nemotron-VL Processor Decompression-Bomb Guard Bypass7.5—
    HighCVE-2026-116176vLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnector8.2—
    HighCVE-2026-116173vLLM 0.22.0 before 0.24.0 Denial of Service via gRPC output_candidates.token_ids7.5—
    HighCVE-2026-116172vLLM 0.22.0 before 0.24.0 DoS via Rust gRPC CandidateTokens.top_n7.5—
    Embed badge

    Show the severity and KEV status of this vulnerability on your site – with a link back here. The image is updated hourly.

    Badge preview for CVE-2026-116172
    <a href="https://intel.neosec.eu/en/cve/CVE-2026-116172"><img src="https://intel.neosec.eu/badge/cve/CVE-2026-116172.svg?lang=en" alt="CVE-2026-116172 – NEOSEC Intel" height="20"></a>