CVE-2026-105757: vllm Input Validation Flaw — Fix

Description

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0.

Is your site exposed to CVE-2026-105757?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

6.5

MEDIUM

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS — Exploit Prediction

0.0031

Probability of exploitation

0.22%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-20 Improper Input Validation

CWE-248 CWE-248

CWE-755 CWE-755

Affected Products

Vendor	Product	Versions
vllm	vllm	< 0.30.0

References

Advisories & Patches

https://github.com/vllm-project/vllm/commit/c55e15a44ec4127832d4a86928a356fdd9e68dbd https://github.com/vllm-project/vllm/pull/51450 https://github.com/vllm-project/vllm/security/advisories/GHSA-85xf-c7hm-whqw

Other References

https://github.com/vllm-project/vllm/releases/tag/v0.30.0

Frequently Asked Questions

What is CVE-2026-105757? +

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0. It has a CVSS v3.1 base score of 6.5 (MEDIUM).

How severe is CVE-2026-105757? +

CVE-2026-105757 has a CVSS v3.1 score of 6.5 out of 10, rated MEDIUM. This is a medium-severity vulnerability that should be remediated as part of regular maintenance. The EPSS score is 0.0031, placing it in the 0th percentile for exploitation probability.

What products are affected by CVE-2026-105757? +

CVE-2026-105757 affects products from vllm, specifically: vllm. Check the affected products table above for specific version ranges.

How do I check if I'm vulnerable to CVE-2026-105757? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2025-13826

Zervit's portable HTTP/web server is vulnerable to remote DoS attacks when a configuration reset request is made. The vulnerability is …

CVE-2026-62658

A security flaw was discovered in certain NETGEAR Nighthawk RAX series routers that could allow someone already logged in to …

CVE-2024-54011

Penetration Testing engineers at Amazon have discovered a flaw where the camera system fails to properly handle data supplied in …

CVE-2026-56349

n8n before version 2.10.0 contains an input validation vulnerability in the Guardrail node that allows attackers to bypass default guardrail …

CVE-2026-6409

A Denial of Service (DoS) vulnerability exists in the Protobuf PHP library during the parsing of untrusted input. Maliciously structured …

CVE-2026-59650

In Bouncy Castle for Java before 1.85, MTI/A0 DH agreement exponentiates unvalidated peer value. This issue also affects Bouncy Castle …

CVE-2026-105757