CVE-2026-34753 — Server-Side Request Forgery in Vllm
Severity
5.4MEDIUMNVD
EPSS
0.0%
top 88.80%
CISA KEV
Not in KEV
Exploit
No known exploits
Affected products
Timeline
PublishedApr 6
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 …
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:LExploitability: 2.8 | Impact: 2.5
Affected Packages2 packages
🔴Vulnerability Details
2📋Vendor Advisories
1Red Hat▶
vllm: vLLM: Server-Side Request Forgery allows access to internal services via controlled batch input↗2026-04-06
🕵️Threat Intelligence
5💬Community
1Bugzilla▶
CVE-2026-34753 vllm: vLLM: Server-Side Request Forgery allows access to internal services via controlled batch input↗2026-04-06