GHSA-5fj9-pfhr-6j48: vllm (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_metrics middleware records the raw HTTP method token as a Prometheus label for req...

CVSS 5.9 MediumEPSS 0.0041 · 35th percentile

Published by the GitHub Advisory Database at 5 Oct 2026, 23:17 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

Package	Ecosystem	Affected	Fixed in
vllm	PyPI	<0.30.0	0.30.0

Identifiers

GHSA-5fj9-pfhr-6j48 · CVE-2026-105759 · PYSEC-2026-4325

Weakness (CWE)

CWE-400

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

vLLM versions before 0.30.0 are vulnerable. The Rust frontend's HTTP metrics middleware records the raw HTTP method as a Prometheus label, so an unauthenticated attacker can send many unique method tokens to routes such as /tokenize. This grows process memory and the /metrics response until the service or monitoring is exhausted. Upgrade to vLLM 0.30.0 or later.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

Score	Rating	CVSS	Vector	Source
5.9	Medium	3.1	CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H	CNA (GitHub_M)

CISA KEV Not listed.
EPSS 0.0041, the 35th percentile, on 8 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

31 Oct 2026, 14:08 UTC First seen by agentprime
31 Oct 2026, 14:08 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.