CVE-2026-34753
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…
Does this matter?
Lower severity and a low EPSS score (0.25%). Track it; it rarely justifies an emergency change on its own.
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.
- CVSS 3.1
- 5.4 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
- EPSS
- 0.25% probability · 16th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-918
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pf3h-qjgv-vcprPatch, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.