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.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-129"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/93xxx/CVE-2026-93592.json"
}