cve.bz

CVE-2026-105922 vllm vllm: Improper Resource Shutdown or Release

2.1 lowEPSS 0.3%Fix available

Low (2.1) in vllm vllm. EPSS 0.3% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.32.0.

On this page
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.

Severity

CVSS 4.0

2.1 low
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

CVSS 3.1

4.3 medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
EPSS
0.3% (unchanged from 0.3% a week ago; 0.3% 30 days ago) estimated probability of exploitation activity in the next 30 days; 24th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: no · Technical impact: partial, assessed 2026-10-06. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-404 Improper Resource Shutdown or Release
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-105922 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-105922?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-105922?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-105922 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
vllm:vllmthrough 0.31.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
PYSEC-2026-4319PyPIvllm<0.32.00.32.0

Linux distributions

DistributionReleasePackageFixed inAdvisory
openSUSETumbleweedpython-vllm0.30.0-2.1openSUSE-SU-2026:12120-1

From the distributions' data via OSV.dev: SUSE security data, CC BY 4.0. Modified: reformatted and linked to CVE records. Credits. On the distributions' own pages: openSUSE.

Red Hat

Red Hat rates this Important.

Red Hat's statement

This vulnerability is rated as an Important severity flaw because an unauthenticated remote client can crash the inference engine without privileges, disrupting service availability for all users. In Red Hat Enterprise Linux AI and Red Hat OpenShift AI environments, vLLM operates as a network-facing model serving backend. When maliciously crafted sampling parameters or penalty options are processed, an unhandled exception abruptly terminates the serving process and halts ongoing model inference operations.

Red Hat's mitigation

Restrict network reachability of the vLLM inference service to authorized networks or localhost to prevent untrusted callers from submitting malicious queries.

On standalone host environments, restrict access to the inference port (default 8000/tcp) using firewalld:

firewall-cmd --permanent --add-rich-rule='rule family="ipv4" source address="<trusted_network>" port port="8000" protocol="tcp" accept'

firewall-cmd --permanent --remove-port=8000/tcp

firewall-cmd --reload

In Red Hat OpenShift AI environments, configure NetworkPolicies to isolate the model-serving pods and restrict ingress traffic exclusively to trusted internal gateways or authorized namespaces.

Caveats: Restricting endpoint reachability blocks external or unauthorized systems from interacting with served models.

Warning: Executing `firewall-cmd --reload` reloads the active firewall configuration and may momentarily interrupt existing network connections.

ProductPackageStateAdvisory
Red Hat OpenShift AI 3.4rhoai/odh-kserve-agent-rhel9:1792685313Fixed 2026-10-29RHSA-2026:92510
Red Hat OpenShift AI 3.4rhoai/odh-kserve-controller-rhel9:1792685196Fixed 2026-10-29RHSA-2026:92510
Red Hat OpenShift AI 3.4rhoai/odh-kserve-router-rhel9:1792688864Fixed 2026-10-29RHSA-2026:92510
Red Hat OpenShift AI 3.4rhoai/odh-kserve-storage-initializer-rhel9:1792685067Fixed 2026-10-29RHSA-2026:92510
Red Hat AI Inference Serverrhaiis/vllm-cpu-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-cuda-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-neuron-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-rocm-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-spyre-rhel9Will not fix
Red Hat AI Inference Serverrhaiis/vllm-tpu-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-cuda-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Will not fix
Red Hat AI Inference Serverrhaii/vllm-rocm-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-spyre-rhel9Affected
Red Hat AI Inference Serverrhaii/vllm-tpu-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-aws-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-rocm-rhel9Affected
7 more in the JSON and on Red Hat's page.

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-105922.

Attack patterns (CAPEC)

  • CAPEC-125 Flooding Likelihood: High · Severity: Medium
  • CAPEC-130 Excessive Allocation Likelihood: Medium · Severity: Medium
  • CAPEC-131 Resource Leak Exposure Likelihood: Medium · Severity: Medium
  • CAPEC-494 TCP Fragmentation
  • CAPEC-495 UDP Fragmentation
  • CAPEC-496 ICMP Fragmentation
  • CAPEC-666 BlueSmacking Likelihood: Medium · Severity: Medium

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON