Skip to main content
VulnerabilityPublished

CVE-2026-105922: vLLM · Denial of Service

Affects vLLMSource CVE Database V5

0
Compare

Public exploit available · CVSS 5.3 Medium.

Data as of 20 Nov 2026, 17:34 UTC

CVSS 4.0 base score
5.3Medium
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.3% chance of exploitation in 30 days – higher than 24% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
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

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 6 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: evidence found.

    CVSS exploit maturity: proof of concept public

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 20 Nov 2026.

What to do

Affected software

ProductAffectedFixed in
vllm-projectvLLMAffected
  • 0.1 – 0.31.0
31 affected builds
Fixed in–
PyPIvllmpkg:pypi/vllmOther threatsAffected
  • <=0.31.0
Fixed in–

CPE configurations (1)

  • cpe:2.3:a:vllm-project:vllm:*:*:*:*:*:*:*:*

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Since the vendor has not responded or released a fix, users should monitor official channels for updates. In the meantime, consider implementing network-level protections to restrict access to the vulnerable component if feasible.

Description

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.

References

Community reviews

Loading reviews…