High severity7.5NVD Advisory· Published Sep 18, 2026· Updated Sep 28, 2026
CVE-2026-93592
CVE-2026-93592
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
2Patches
Vulnerability mechanics
References
2- github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpfnvdExploitMitigationPatchVendor Advisory
- www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-negative-token-idnvdThird Party Advisory
News mentions
1- VLLM: Batch of 17 Vulnerabilities Disclosed, Affecting LLM Inference Engine StabilityVypr Intelligence · Sep 21, 2026