vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-440"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/114xxx/CVE-2026-114049.json"
}{
"extracted_events": [
{
"range": [
{
"introduced": "0"
},
{
"fixed": "0.31.0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
}
]
}