CVE Intelligence
Skip to main content
mediumDenial of Servicepublic exploit

CVE-2026-105922

CVE-2026-105922 — vllm-project vLLM Penalty utils.py get_token_bin_counts_and_mask denial of service

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.

Published Updated Sources: NVD, vllm-project (CNA), GitHub, GitHub Security Advisory, SOCRadar CTI

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the scoring sources call it.

Exploitation

Exploit code

public exploit, none observed

EPSS

0%

ahead of 0% of scored CVEs

Affects

vllm-project

31 products listed

CVSS base

4.3

medium · 6 sources

Remediation

The vendor's own words where we have them.

Upgrade vLLM to a fixed release. Apply vendor patches per advisory and restrict external exposure of the affected component until patched.

First 24 hours

Ordered from the record's own fields — exposure first, because you cannot patch what you have not found.

  • Identify exposed assets running affected vendor/product/version combinations.
  • Prioritize based on EPSS, PoC availability, and external exposure.
  • Search available logs for exploit probes, errors, authentication anomalies, or suspicious child processes matching the vulnerability class.

Affected scope

Vendor, product and version as the advisories word them.

VendorProductVersionsStatus
vllm-projectvLLM0.1Vulnerable
vllm-projectvLLM0.2Vulnerable
vllm-projectvLLM0.3Vulnerable
vllm-projectvLLM0.4Vulnerable
vllm-projectvLLM0.5Vulnerable
vllm-projectvLLM0.6Vulnerable
vllm-projectvLLM0.7Vulnerable
vllm-projectvLLM0.8Vulnerable
vllm-projectvLLM0.9Vulnerable
vllm-projectvLLM0.10Vulnerable
vllm-projectvLLM0.11Vulnerable
vllm-projectvLLM0.12Vulnerable

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Availability

Low

Confidentiality

None

Integrity

None

Scope

Unchanged

Attack Complexity

Low

Attack Vector

Network

Privileges Req

Low

User Interaction

None

Every base score collected

Sources score independently and disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactSource
4.3CVSS 3.1medium2.81.4NVD, GHSA
4CVSS 2.0medium82.9vuldb.com (CNA)
5.3CVSS 4.0medium——vllm-project (CNA)
4.3CVSS 3.1medium——vllm-project (CNA)
4.3CVSS 3.0medium——vllm-project (CNA)
4CVSS 2.0medium——vllm-project (CNA)

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L

What this weakness leads to

MITRE's own consequences and mitigations for the weakness class — the authority's wording, not guidance derived from the CVSS vector.

MITRE

CWE-404 · Improper Resource Shutdown or Release

  • DoS: Resource Consumption (Other)
  • Varies by Context
  • Read Application Data

Mitigation: Use a language that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid. For example, languages such as Java, Ruby, and Lisp perform automatic garbage collection that releases memory for objects that have been deallocated.

Weakness & attack patterns

  • CWE-404Improper Resource Shutdown or Release

Attack patterns reported against this CVE. The ATT&CK techniques below are inferred from its weakness class.

CAPEC-496 · ICMP FragmentationCAPEC-495 · UDP FragmentationCAPEC-494 · TCP FragmentationCAPEC-125 · FloodingCAPEC-130 · Excessive AllocationCAPEC-131 · Resource Leak Exposure
  • T1498.001Network Denial of Service: Direct Network Flood
  • T1499Endpoint Denial of Service
  • T1499.003Endpoint Denial of Service: Application Exhaustion Flood

Public exploit

Capability, not use: code existing is a different claim from anyone running it.

Repositories

1

Detection

Read off the CVSS vector and the weakness class. Starting points, not rules we have tested.

  • Search application, proxy, and WAF logs for requests touching /model_executor/layers/utils.py.
  • Prioritize edge telemetry for network-reachable vLLM.
  • Monitor for scanner or exploit-pattern traffic after 1 public PoC repositories were reported.
web/proxy/WAF logsapplication logsnetwork IDS/IPS

Timeline

What happened to this CVE, newest first — with the readings a source repeats on a schedule counted underneath rather than listed.

  1. 2026
  2. Added · CVSS 3.1 4.3 (AV:N)

    Oct 6, 2026 · NVD

  3. Initial · CVE published

    Oct 6, 2026 · NVD

  4. Reported · Advisory disclosed

    Oct 6, 2026 · vllm-project

  5. Reported · VulDB entry created

    Oct 6, 2026 · vllm-project

  6. Reported · VulDB entry last update

    Oct 6, 2026 · vllm-project

  7. Added · GHSA-x9pq-jx6q-p3qv published (low)

    Oct 6, 2026 · GitHub Security Advisory

  8. CVE published by MITRE.

    Oct 6, 2026 · SOCRadar CTI

References

9 on the record

Elsewhere on this site

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.
Answered from this record1

What should defenders know first?

CVE-2026-105922 is vllm-project vLLM Penalty utils.py get_token_bin_counts_and_mask denial of service, a medium vulnerability affecting vLLM from vllm-project. The current evidence does not list it in CISA KEV, and the exploit status is: Active exploitation is not confirmed from current sources for CVE-2026-105922. Public exploit evidence is: 1 public PoC repositories reported; 0 marked weaponized in current dataset. The affected-version evidence is listed in the key facts and affected products tables. Defenders should first verify whether exposed or business-critical assets run those versions, then apply vendor patches or mitigations, restrict reachable attack surface, and preserve logs for detection review. CVSS 4.3 describes technical severity, while EPSS 0% helps estimate near-term exploit likelihood; neither replaces asset context. Unknown fields should remain explicit in tickets, and threat actor, IOC, victimology, or payload claims should not be added unless a cited source supports them. Monitor CISA KEV, vendor advisories, NVD changes, public PoC repositories, and internal telemetry for update triggers.