Menu

Star on GitHub · 3.5k

CVE-2026-93840

3.7 · LOW

vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids().

Published Sep 18, 2026vllmCWE-129EPSS 0.25%

Overview

CVE-2026-93840 is a low-severity vulnerability affecting vllm vllm. It was published on September 18, 2026 and has a CVSS 3.1 base score of 3.7 (LOW).

This vulnerability has a CVSS 3.1 base score of 3.7, rated LOW. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

Technical description

vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.

Remediation

Check the references section for vendor advisories and patches from vllm. Update vllm to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

Affected products

VendorProductVersionsStatus
vllmvllm>= 0, < 0.29.0Affected

Frequently asked questions

What is CVE-2026-93840?

CVE-2026-93840 is a low-severity vulnerability affecting vllm vllm. It was published on September 18, 2026 and has a CVSS 3.1 base score of 3.7 (LOW).

How severe is CVE-2026-93840?

This vulnerability has a CVSS 3.1 base score of 3.7, rated LOW. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

How do I fix or remediate CVE-2026-93840?

Check the references section for vendor advisories and patches from vllm. Update vllm to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

How can CyberStrike help with CVE-2026-93840?

CyberStrike is an open-source, AI-augmented pentesting engine. Rather than flag a version number, it tests whether an issue like CVE-2026-93840 is actually reachable in your own applications and APIs, then verifies each finding before reporting it. That tells you if the weakness is a real, exploitable risk in your environment or a false positive you can safely deprioritize.

Related LOW CVEs from 2026

View all
CyberStrike v2 is here — more intelligence, greater reach