CVE-2026-105759: vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metri
Summary
vLLM, a system for running large language models, has a vulnerability in versions before 0.30.0 where an attacker can send fake HTTP method tokens (the commands in web requests) to unprotected routes, causing the system to create unlimited memory-consuming tracking records in Prometheus (a monitoring tool that tracks system performance). This eventually crashes the service by using up all available memory.
Solution / Mitigation
Update vLLM to version 0.30.0 or later, where this issue is fixed.
Vulnerability Details
5.9(medium)
EPSS: 0.0%
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
network
high
none
none
October 5, 2026
Classification
Affected Vendors
Related Issues
CVE-2026-47482: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause missing release of memory
CVE-2022-29200: TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, the implem
Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-105759
First tracked: October 5, 2026 at 08:07 PM
Classified by LLM (prompt v3) · confidence: 95%