vLLM API endpoints vulnerable to Denial of Service Attacks (vllm-project vllm)
At a glance
- Source
- NVD
- EPSS
- EPSS 0.56 % · percentile 47 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Analyzed
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.
Weaknesses (CWE)
- CWE-400 — Uncontrolled Resource Consumption
References
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 3.1 | HIGH 7.5 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | GitHub_M |
| CVSS 3.1 | HIGH 7.5 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | NVD · security-advisories@github.com (Secondary) |
Advisories
- GHSA-rxc4-3w6r-4v47 — vllm API endpoints vulnerable to Denial of Service Attacks
- PYSEC-2026-2021 — vllm API endpoints vulnerable to Denial of Service Attacks
European references
- ENISA EUVD · EUVD-2025-25446
- GCVE · GCVE-0-2025-48956
CERT-FR advisories
- CERTFR-2025-AVI-1057 — Multiples vulnérabilités dans les produits VMware · cert.ssi.gouv.fr
Affected configurations (NVD CPE)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*≥ 0.1.0 < 0.10.1.1
Affected products
| Product | Versions |
|---|---|
| vllm-project · vllm | affected >= 0.1.0, < 0.10.1.1 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| CERT-FR (ANSSI) | Licence Ouverte / Etalab 2.0 |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |