vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense
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.
CVE-2026-114049
Primary source · Revision 1
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
Security context
Source reference: cve:CVE-2026-114049
vllm
Source reference: /containers/cna/affected/0/product
- Affected versions
- Not stated in this record
- Fixed versions
- Not stated in this record
- Prerequisites
- Not stated in this record
Structured affected-version data
Original package identities and version rules from this source.
[
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "0.31.0",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "0.31.0",
"versionType": "semver"
}
],
"packageURL": "pkg:pypi/vllm",
"defaultStatus": "unaffected"
}
]- Related CVEs
- CVE-2026-114049
Source reference:
/cveMetadata/cveId
Publisher severity
medium
Source reference: /containers/cna/metrics
- Event
- #44942 · Revision 1
- Added to Heist Feed
- Publisher date