Advisory record · GHSA-3f6c-7fw2-ppm4

vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class

CVSS 7.1 HighEPSS 0.0025 · 16th percentile

Published by the GitHub Advisory Database at 7 Oct 2025, 22:14 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
vllmPyPI>=0.5.0, <0.11.00.11.0
Identifiers
GHSA-3f6c-7fw2-ppm4 · CVE-2025-6242 · PYSEC-2026-2011
Weakness (CWE)
CWE-601 · CWE-918
Published
7 Oct 2025
Updated
10 Sept 2026

Machine-written summary

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

Versions of vllm from 0.5.0 before 0.11.0 are affected by a server-side request forgery flaw in the MediaConnector class, where the load_from_url and load_from_url_async methods fetch user-supplied URLs without adequate host restrictions. An attacker who can submit requests to the server can make it send requests to internal network resources, which could expose internal services or enable network scanning. Upgrade to vllm 0.11.0 or later. As a workaround, the --allowed-media-domains option can restrict which domains media URLs may point to.

Written 5 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

ScoreRatingCVSSVectorSource
7.1 High 3.1 CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:H CNA (redhat)
  • CISA KEV Not listed.
  • EPSS 0.0025, the 16th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:34 UTC First seen by agentprime
  2. 31 Oct 2026, 14:34 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.