Skip to content
Fencer Intel
medium 4.3

CVE-2026-105922 json

vllm-project vLLM Penalty utils.py get_token_bin_counts_and_mask denial of service

published last mo. modified 22d ago also PYSEC-2026-4319 , EUVD-2026-93430

cvss
4.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 24%
public exploits
0
none known

Summary

A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file vllm/model_executor/layers/utils.py of the component Penalty Handler. Performing a manipulation results in denial of service. Remote exploitation of the attack is possible. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.

Patch / fix

  • pypi vllm 0.32.0
  • python-vllm openSUSE Tumbleweed 0.30.0-2.1

opensuse advisories openSUSE-SU-2026:12120-1

Is CVE-2026-105922 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-2026-105922 updated cvss 7.5

vllm: vLLM: Denial of Service via crafted inference request with prompt embeddings

  • Red Hat AI Inference Server rhaii/vllm-cpu-rhel9, rhaii/vllm-tpu-rhel9, rhaii/vllm-cuda-rhel9, rhaii/vllm-rocm-rhel9, rhaiis/vllm-tpu-rhel9, rhaii/vllm-gaudi-rhel9, +3 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9, +1 more 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 OpenShift AI 3.4 rhoai/odh-kserve-agent-rhel9 1792685313, rhoai/odh-kserve-router-rhel9 1792688864, rhoai/odh-kserve-controller-rhel9 1792685196, rhoai/odh-kserve-storage-initializer-rhel9 1792685067
    fixed: vendor fix RHSA-2026:92510
  • Red Hat AI Inference Server rhaiis/vllm-cpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaiis/vllm-neuron-rhel9
    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 1792722177, rhoai/rhai-cli-rhel9 1792722177, rhoai/odh-automl-rhel9 1792697253, rhoai/odh-mlflow-rhel9 1793002327, rhoai/odh-autorag-rhel9 1793265800, rhoai/odh-trainer-rhel9 1792817113, +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
no
Technical impact
partial
Assessed
last mo.

Exploit prediction

0.31% chance of exploitation in the next 30 days, higher than 24% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • gist.github.com https://gist.github.com/Yunzez/5c70a3bb328eaf6d646b9d31e879dc4a#file-repro_prompt_embeds_penalties_engine_crash-py referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 4.0 5.3 CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P
CNA 3.1 4.3 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:X/RC:C
CNA 3.0 4.3 CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:X/RC:C
CNA 2.0 4.0 AV:N/AC:L/Au:S/C:N/I:N/A:P/E:POC/RL:ND/RC:C
CNA 4.0 2.1 CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P/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
CNA 3.1 4.3 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
CNA 2.0 4.0 AV:N/AC:L/Au:S/C:N/I:N/A:P

Affected packages

ecosystem package affected fixed in
pypi vllm
<0.32.0
0.32.0

Affected products

  • vllm-project vLLM

Classification

Weakness
  • CWE-404 Improper Resource Shutdown or Release

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.