{"id":"CVE-2026-114052","published":"2026-10-21T01:17:27.943","lastModified":"2026-10-22T19:17:36.780","description":"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.","cvssScore":7.5,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","cwes":["CWE-770"],"vendors":[],"products":[],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-823j-m4cj-hmjf","tags":[]},{"url":"https://www.vulncheck.com/advisories/vllm-0.25.0-before-0.31.0-moss-audio-memory-exhaustion-via-tokenize-mm-processor-kwargs","tags":[]}],"exploitRefs":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-823j-m4cj-hmjf","tags":[]}],"hasPoc":true,"ai":null}