PoC Index

CVE-2026-34753

MEDIUM 5.4EPSS 0.2%

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 v3.1
5.4 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
CVSS v3.1
5.4 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
EPSS
0.25% chance of exploitation in the next 30 days, 16th percentile
Published
2026-04-06
Updated
2026-04-07

Proof-of-concept exploits (1)

References

Related