CVE-2026-116181

MEDIUMCVSS 6.5/10

Last modified

CVE-2026-116181 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer..

Description

vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.

Metrics

Weakness Enumeration

Affected Software

Source: CNA advisory (CVE.org). NVD analysis pending.

VendorProductVersions
vllm-projectvllm>= 0.20.1, < 0.29.0

References

Timeline

Published
Last Modified
Status
Awaiting Analysis

Frequently Asked Questions

What is CVE-2026-116181?
vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.
How severe is CVE-2026-116181?
CVE-2026-116181 has a CVSS score of 6.5/10 (MEDIUM severity).
How do I fix CVE-2026-116181?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

Are you affected by CVE-2026-116181?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST