CVE-2026-34753
vLLM affected by Server-Side Request Forgery (SSRF) in download_bytes_from_url
- Published
- Apr 6, 2026
- Updated
- Apr 7, 2026
- Assigning CNA
- GitHub_M
- Evidence observed
- Aug 26, 2026
Primary CVSS
nvd · CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:LLow · next 30 days
- Percentile
- 16.1%
- Model date
- Sep 21, 2026
EPSS is a statistical estimate, not a certainty or a measure of impact. Combine it with CVSS, KEV status, exposure and your environment.
Summary
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.
Sources
1Proof-of-concept exploit for CVE-2026-34753, demonstrating the vulnerability and potential impact.
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.