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.
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
Published: 2026-09-18
Updated: 2026-09-18
Base Score: 7.8
Vector: CVSS2#AV:N/AC:L/Au:N/C:N/I:N/A:C
Severity: High
Base Score: 7.5
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Severity: High
Base Score: 8.7
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Severity: High
EPSS: 0.00377