Skip to content
Fencer Intel
high 7.5

CVE-2026-93592 json

vLLM before 0.28.0 Denial of Service via negative token ID

published 2mo ago modified last mo. also EUVD-2026-82911 , GHSA-25q3-v2hm-8vpf , PYSEC-2026-3997

cvss
7.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 46%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi vllm 0.28.0
  • vllm-project vllm 0.28.0

Is CVE-2026-93592 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-93592 updated cvss 7.5

vllm: vLLM: Denial of Service via negative token ID input

  • Red Hat AI Inference Server rhaii/vllm-tpu-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaii/vllm-neuron-rhel9, +2 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-llm-d-kv-cache-rhel9
    affected: workaround, no fix available, no fix planned “Will not fix”
  • Red Hat AI Inference Server 3.4 rhaii/vllm-cpu-rhel9 1791857301, rhaii/vllm-cuda-rhel9 1791857183, rhaii/vllm-rocm-rhel9 1791856725, rhaii/vllm-spyre-rhel9 1791858592
    fixed: vendor fix RHSA-2026:83112
  • Red Hat AI Inference Server 3.5 rhaii/vllm-cpu-rhel9 1793444554, rhaii/vllm-cuda-rhel9 1793444600, rhaii/vllm-rocm-rhel9 1793444456, rhaii/vllm-gaudi-rhel9 1791427182, rhaii/vllm-gaudi-rhel9 1793444510, rhaii/vllm-spyre-rhel9 1793444409
    fixed: vendor fix RHSA-2026:94702
  • Red Hat Enterprise Linux AI 3.4 rhelai3/bootc-rocm-rhel9 1792612921, rhelai3/bootc-azure-rocm-rhel9 1792680669
    fixed: vendor fix RHSA-2026:90440
  • Red Hat OpenShift AI 3.4 rhoai/odh-kserve-agent-rhel9 1791468381, rhoai/odh-kserve-router-rhel9 1791468401, rhoai/odh-kserve-controller-rhel9 1791468368, rhoai/odh-kserve-storage-initializer-rhel9 1790958549
    fixed: vendor fix RHSA-2026:84734
  • Red Hat Enterprise Linux AI 3.4 rhelai3/bootc-cuda-rhel9 1792612985, rhelai3/bootc-aws-cuda-rhel9 1792680701, rhelai3/bootc-gcp-cuda-rhel9 1792680694, rhelai3/bootc-azure-cuda-rhel9 1792680694
    not affected: vulnerable code not present
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-th-torch-cuda-py312-rhel9
    not affected: vulnerable code not in execute path
  • Red Hat OpenShift AI 3.4 rhoai/odh-cli-rhel9 1791509689, rhoai/rhai-cli-rhel9 1791509689, rhoai/odh-automl-rhel9 1791535789, rhoai/odh-mlflow-rhel9 1791865967, rhoai/odh-autorag-rhel9 1791557539, rhoai/odh-trainer-rhel9 1791869783, +96 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
last mo.

Exploit prediction

0.54% chance of exploitation in the next 30 days, higher than 46% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 4.0 8.7 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
CNA 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CNA 4.0 8.7 CVSS:4.0/AV:N/AC:L/AT:N/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

Affected packages

ecosystem package affected fixed in
pypi vllm
<0.28.0
0.28.0

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-129 Improper Validation of Array Index

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of vllm-project/vllm published their own advisory on GitHub. Reviewed sources take precedence over it.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.