CVE-2026-34753

MEDIUM

5.4

Description

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.

Details CVE

Score CVSS v3.15.4

SeveriteMEDIUM

Vecteur CVSSCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L

Vecteur d'attaqueNETWORK

ComplexiteLOW

Privileges requisLOW

Interaction utilisateurNONE

Publie4/6/2026

Derniere modification4/6/2026

Sourcenvd

Observations honeypot0

Faiblesses (CWE)

CWE-918

References

https://github.com/vllm-project/vllm/security/advisories/GHSA-pf3h-qjgv-vcpr(security-advisories@github.com)

Correlations IOC

Aucune correlation enregistree

This product uses data from the NVD API but is not endorsed or certified by the NVD.