CVE-2026-34753

Affects: large language model, vLLM

CVSS: MEDIUM · 5.4 v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
Published: 2026-04-06
Weakness: CWE-918
Source: nvd.nist.gov/vuln/detail/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.

References

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

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-34753 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course → · Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming