CVE-2026-105922
Description
A flaw was found in vLLM. A remote attacker can exploit this vulnerability by sending manipulated input processed by the penalty handling mechanism. This triggers an unhandled failure in the token bin counting routine (get_token_bin_counts_and_mask), crashing the service and resulting in a Denial of Service (DoS).
Statement
A flaw in the vLLM inference engine, rated by Red Hat with an impact of IMPORTANT, affects Red Hat AI Inference Server and Red Hat OpenShift AI (RHOAI) releases that ship vLLM. A remote attacker can send a crafted inference request that combines prompt embeddings with sampling penalty parameters; when processed by the penalty handling mechanism, this triggers an unhandled failure in the token bin counting routine get_token_bin_counts_and_mask, crashing the model-serving engine and causing a denial of service until the service is restarted. A proof-of-concept exploit has been made public. Red Hat's severity (CVSS:3.1 base score 7.5, IMPORTANT) is higher than the upstream rating (4.3, Moderate) because the vLLM API server does not require authentication by default, so an unauthenticated remote attacker can repeatedly crash the service and fully impact availability. The flaw does not compromise confidentiality or integrity. All affected Red Hat product streams are assessed as affected, and a fix is being pursued through the responsible product teams.
Mitigation
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
The following CVSS metrics and score provided are preliminary and subject to review.
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 7.5 | N/A | 4.3 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | Low | N/A | Low |
| Privileges Required | None | N/A | Low |
| User Interaction | None | N/A | None |
| Scope | Unchanged | N/A | Unchanged |
| Confidentiality | None | N/A | None |
| Integrity Impact | None | N/A | None |
| Availability Impact | High | N/A | Low |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
cve.org: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RC:C
Understanding the Weakness (CWE)
Availability,Confidentiality
Technical Impact: DoS: Crash, Exit, or Restart; Read Application Data
An uncaught exception could cause the system to be placed in a state that could lead to a crash, exposure of sensitive information or other unintended behaviors.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
