vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
Title source: cnaExploitation Summary
EIP tracks 1 public exploit for CVE-2026-34753. PoCs published by Dhiaelhak-Rached.
AI-analyzed exploit summary This repository contains a functional proof-of-concept for CVE-2026-34753, demonstrating an SSRF vulnerability in vLLM's batch API. The exploit leverages the lack of URL validation in the `download_bytes_from_url` function to access internal services, such as a simulated AWS metadata service.
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.
Exploits (1)
This repository contains a functional proof-of-concept for CVE-2026-34753, demonstrating an SSRF vulnerability in vLLM's batch API. The exploit leverages the lack of URL validation in the `download_bytes_from_url` function to access internal services, such as a simulated AWS metadata service.
References (1)
Scores
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L