Detections
Analytics
SCA: security update for vllm (GHSA-8wr5-jm2h-8r4f)
high Tenable Self-Hosted Container Security Plugin ID 444833
Description
There are packages installed that are affected by a vulnerability referenced in the following CVE:- vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a
frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a
recovered token equal to the model vocabulary size boundary value, which is then converted to negative one
when the engine selects the next live token for a request and is written back into the drafter's input
ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and
crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is
reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send
generation requests can crash the shared engine worker, aborting concurrent requests and causing a
service-wide denial of service for other clients of the deployment until the worker is restarted. This
issue is fixed in version 0.24.0. (CVE-2026-54234)
Solution
Update the vllm library and its related packages to version 0.24.0 or later.See Also
Plugin Details
Severity: High
ID: 444833
Version: Revision 1.1
Type: Local
Family: SCA Checks
Published: 7/17/2026
Updated: 7/17/2026
Risk Information
VPR
Risk Factor: Low
Score: 3
Percentile: 23.75
Vendor
Vendor Severity: High
CVSS v2
Risk Factor: High
Base Score: 7.8
Temporal Score: 6.1
Vector: CVSS2#AV:N/AC:L/Au:N/C:N/I:N/A:C
CVSS Score Source: CVE-2026-54234
CVSS v3
Risk Factor: High
Base Score: 7.5
Temporal Score: 6.7
Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Temporal Vector: CVSS:3.0/E:P/RL:O/RC:C
Vulnerability Information
Exploit Available: true
Exploit Ease: Exploits are available
Patch Publication Date: 7/17/2026
Vulnerability Publication Date: 7/6/2026
Reference Information
CVE: CVE-2026-54234
cwe: CWE-20