CVE-2026-116177 vLLM 0.10.2 before 0.25.0 DoS via Nemotron-VL Processor Decompression-Bomb Guard Bypass
- Exploited in the wild
- Not known
- Fix
- Available
What is CVE-2026-116177?
CVE-2026-116177 is a high-severity vulnerability in Vllm Vllm, published on 25 Oct 2026.
Official 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.
Weakness: CWE-400
Which versions are affected by CVE-2026-116177?
1 open source package ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.10.2 | 0.25.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-116177?
Upgrade vllm to 0.25.0 or later.
Is CVE-2026-116177 being exploited?
There is no known exploitation of CVE-2026-116177 in the wild and no public exploit code.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-mm38-5g96-7j6x, GHSA-p9gm-63qh-x2pq, PYSEC-2026-4352.