| Component | vLLM |
| Severity | high (CVSS 7.5) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H |
| Published (NVD) | 2026-10-25 |
| Affected versions | >= 0.10.2, < 0.25.0 from the CVE Program record written by the CNA that assigned the CVE |
| Fixed in | 0.25.0 |
| Weakness | CWE-400 |
| CISA KEV | not listed |
NVD description
vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the Nemotron-VL processors globally set Image.MAX_IMAGE_PIXELS to None. Attackers can submit a pathological decompression-bomb image to /v1/chat/completions to OOM-kill the worker and deny service to co-tenants.
What to do
- Upgrade vLLM to
0.25.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-116177
- https://github.com/vllm-project/vllm/security/advisories/GHSA-mm38-5g96-7j6x
- https://www.vulncheck.com/advisories/vllm-0.10.2-before-0.25.0-dos-via-nemotron-vl-processor-decompression-bomb-guard-bypass