vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-20"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/100xxx/CVE-2026-100652.json"
}