CVE-2026-34753

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.

PUBLISHED Reserved 2026-03-30 | Published 2026-04-06 | Updated 2026-04-07 | Assigner GitHub_M

Problem types

CWE-918: Server-Side Request Forgery (SSRF)

Product status

References

github.com/...t/vllm/security/advisories/GHSA-pf3h-qjgv-vcpr

cve.org (CVE-2026-34753)

nvd.nist.gov (CVE-2026-34753)

Download JSON