CVE-2026-114052

vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs

State: Published
Severity: 8.7 High
Published: Oct 21, 2026
Updated: Oct 22, 2026
Reserved: Oct 20, 2026

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.

Scores

CVSS	Score	Vector	Source
4.0	8.7 High	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	VulnCheck
3.1	7.5 High	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H	VulnCheck

Weaknesses

CWE-770 Allocation of Resources Without Limits or Throttling

Affected Products

Product	Versions
vllmvllm-project	0.25.0 to before 0.31.0Affected 0.31.0Not affected

References

GitHub Security Advisory (GHSA-823j-m4cj-hmjf)vendor-advisory
VulnCheck Advisory: vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargsthird-party-advisory

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.