CVE-2026-93592

EUVD-2026-82911
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.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
VulnCheckCNA
7.5 HIGH
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Base Score
CVSS 3.x
EPSS Score
Percentile: Unknown
Early Detection
Affected products identified ahead of NVD analysis through intelligence sources.
VendorProductVersionSource
vllmvllm
𝑥
< 0.28.0
CNA
Common Weakness Enumeration
References
https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf
https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-negative-token-id
https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf