{"affected":[{"database_specific":{"source":"https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4361.yaml"},"ecosystem_specific":{},"package":{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm"},"ranges":[{"events":[{"introduced":"0.24.0"},{"fixed":"0.31.0"}],"type":"ECOSYSTEM"}],"versions":["0.24.0","0.25.0","0.25.1","0.26.0","0.27.0","0.27.1","0.28.0","0.29.0","0.30.0"]}],"aliases":["CVE-2026-114052","GHSA-823j-m4cj-hmjf"],"details":"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.","id":"PYSEC-2026-4361","modified":"2026-11-04T11:00:04.171049902Z","published":"2026-10-21T01:17:27.943Z","references":[{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-823j-m4cj-hmjf"},{"type":"ADVISORY","url":"https://www.vulncheck.com/advisories/vllm-0.25.0-before-0.31.0-moss-audio-memory-exhaustion-via-tokenize-mm-processor-kwargs"}],"schema_version":"1.9.2","severity":[{"score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","type":"CVSS_V4"}]}