vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs
vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized mel_config values to the /tokenize endpoint, which bypasses --api-key, to exhaust host memory and crash the API process.
CVE-2026-114052
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-2026-114052
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": "0.25.0",
"lessThan": "0.31.0",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "0.31.0",
"versionType": "semver"
}
],
"packageURL": "pkg:pypi/vllm",
"defaultStatus": "unaffected"
}
]- Related CVEs
- CVE-2026-114052
Source reference:
/cveMetadata/cveId
Publisher severity
high
Source reference: /containers/cna/metrics
- Event
- #52247 · Revision 1
- Added to Heist Feed
- Publisher date