CVE-2026-54234
Description
A flaw was found in vLLM, a high-throughput and memory-efficient inference and serving engine for Large Language Models (LLMs). A remote attacker can exploit this vulnerability by sending a specially crafted multi-request speculative decoding workload through public gRPC Generate and Abort endpoints. This malformed workload can cause the rejection sampler to produce an out-of-vocabulary token, which then crashes the engine worker. This leads to a service-wide Denial of Service (DoS) for all clients until the worker is restarted.
Statement
This Important denial of service flaw in vLLM, utilized by Red Hat AI Inference Server, Red Hat Enterprise Linux AI, and Red Hat OpenShift AI, allows a remote attacker to crash the engine worker. By sending a specially crafted multi-request speculative decoding workload to public gRPC endpoints, an attacker can trigger an out-of-vocabulary token, leading to a service-wide disruption for all connected clients.
Mitigation
To mitigate this issue, restrict network access to the vLLM inference engine's gRPC Generate and Abort endpoints. Configure firewall rules to limit incoming connections to trusted clients or internal networks only. This will prevent remote, unauthenticated attackers from sending malformed workloads and triggering a denial of service. If the service is exposed via a proxy or load balancer, ensure that access controls are in place at that layer.
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 | 7.5 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | Low | N/A | Low |
| Privileges Required | None | N/A | None |
| 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 | High |
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:N/UI:N/S:U/C:N/I:N/A:H
Understanding the Weakness (CWE)
Confidentiality
Technical Impact: Read Memory
An attacker could get secret values such as cryptographic keys, PII, memory addresses, or other information that could be used in additional attacks.
Confidentiality
Technical Impact: Bypass Protection Mechanism
Out-of-bounds memory could contain memory addresses or other information that can be used to bypass ASLR and other protection mechanisms in order to improve the reliability of exploiting a separate weakness for code execution.
Availability
Technical Impact: DoS: Crash, Exit, or Restart
An attacker could cause a segmentation fault or crash by causing memory to be read outside of the bounds of the buffer. This is especially likely when the code reads a variable amount of data and assumes that a sentinel exists to stop the read operation, such as a NUL in a string.
Other
Technical Impact: Varies by Context
The read operation could produce other undefined or unexpected results.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
