CVE-2026-34753

vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `

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.

Scores

Faiblesses (CWE)

• CWE-918

Avis

• GHSA-pf3h-qjgv-vcpr — vLLM: Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
• PYSEC-2026-3410 — vLLM: Server-Side Request Forgery (SSRF) in `download_bytes_from_url `

Références européennes

• ENISA EUVD · EUVD-2026-19349
• GCVE · GCVE-0-2026-34753

Configurations affectées (CPE NVD)

• cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.16.0 < 0.19.0

Produits affectés

Références

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

Sources