CVSS 3.1
5.4 mediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:LCVE-2026-34753
Medium (5.4) in vllm vllm. EPSS 0.2% chance of exploitation in the next 30 days. Fixed in vllm 0.19.0.
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.
Severity
- EPSS
- 0.2% chance of exploitation in the next 30 days; higher than 15% of CVEs (scores of 2026-10-31)
- CWE
- CWE-918
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-pf3h-qjgv-vcpr | PyPI | vllm | >=0.16.0 <0.19.0 | 0.19.0 |
| PYSEC-2026-3410 | PyPI | vllm | >=0.16.0 <0.19.0 | 0.19.0 |