CVE-2026-93592 vLLM before 0.28.0 Denial of Service via negative token ID

What is CVE-2026-93592?

CVE-2026-93592 is a high-severity denial of service vulnerability in Vllm Vllm, published on 18 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that poisons the GPU context, causing all subsequent requests to fail until the process restarts.

Weakness: CWE-129

Which versions are affected by CVE-2026-93592?

1 open source package ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-93592?

Upgrade vllm to 0.28.0 or later.

Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.

Is CVE-2026-93592 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-93592 exists.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• GitHub advisory
• How this page is made

Also known as GHSA-25q3-v2hm-8vpf, GHSA-c3vq-r33v-49cr, MINI-27qv-wqcq-9f6r, MINI-3pxm-xj6f-4frv, MINI-mpwq-r93g-82r6, PYSEC-2026-3997.