{"id":"CVE-2026-93592","published":"2026-09-18T14:19:10.267","lastModified":"2026-09-22T20:25:55.870","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.","cvssScore":7.5,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","cwes":["CWE-129"],"vendors":[],"products":[],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf","tags":[]},{"url":"https://www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-service-via-negative-token-id","tags":[]},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf","tags":[]}],"exploitRefs":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf","tags":[]},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm-8vpf","tags":[]}],"hasPoc":true,"ai":null}