Skip to content
Fencer Vulns
medium 5.4

CVE-2026-34753 json

vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `

published 2026-04-03 7 mo ago modified 2026-09-10 1 mo ago also EUVD-2026-19349 , GHSA-pf3h-qjgv-vcpr , PYSEC-2026-3410

cvss
5.4
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 17%
public exploits
0
none known

Summary

vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side request forgery (SSRF) vulnerability in download_bytes_from_url allows any actor who can control batch input JSON to make the vLLM batch runner issue arbitrary HTTP/HTTPS requests from the server, without any URL validation or domain restrictions. This can be used to target internal services (e.g. cloud metadata endpoints or internal HTTP APIs) reachable from the vLLM host. This vulnerability is fixed in 0.19.0.

Patch / fix

  • pypi vllm 0.19.0
  • vllm-project vllm 0.19.0
  • vllm vllm 0.19.0

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-34753 updated cvss 5.4

vllm: vLLM: Server-Side Request Forgery allows access to internal services via controlled batch input

  • Red Hat AI Inference Server rhaiis/vllm-tpu-rhel9, rhaiis/vllm-neuron-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-cpu-rhel9, rhoai/odh-vllm-cuda-rhel9, rhoai/odh-vllm-rocm-rhel9, rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, +2 more
    affected: workaround, no fix available “Fix deferred”
  • Red Hat AI Inference Server 3.4 rhaii/vllm-cpu-rhel9 1787151769, rhaii/vllm-cuda-rhel9 1787151771, rhaii/vllm-rocm-rhel9 1787151774, rhaii/vllm-spyre-rhel9 1787151840
    fixed: vendor fix RHSA-2026:57380
  • Red Hat Enterprise Linux AI 3.4 rhelai3/bootc-cuda-rhel9 1787243961, rhelai3/bootc-rocm-rhel9 1787244006, rhelai3/bootc-aws-cuda-rhel9 1787253912, rhelai3/bootc-gcp-cuda-rhel9 1787253774, rhelai3/disk-image-cuda-rhel9 1787310717, rhelai3/bootc-azure-cuda-rhel9 1787253989, +1 more
    fixed: vendor fix RHSA-2026:59151

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
7 mo ago

Exploit prediction

0.26% chance of exploitation in the next 30 days, higher than 17% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 5.4 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
GitHub 3.1 5.4 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
OSV 3.1 5.4 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L

Affected packages

ecosystem package affected fixed in
pypi vllm
>=0.16.0, <0.19.0
0.19.0

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-918 Server-Side Request Forgery

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.