VulnerabilityAnalyzed

CVE-2026-100648

vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat audio decoding, allowing unauthenticated clients to bypass file size restrictions.

MEDIUM 6.9EPSS 0.35%

Does this matter?

Lower severity and a low EPSS score (0.35%). Track it; it rarely justifies an emergency change on its own.

Description

vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat audio decoding, allowing unauthenticated clients to bypass file size restrictions. Attackers can submit oversized audio files through chat endpoints to consume excessive memory and CPU resources during decoding.

CVSS 4.0: 6.9 MEDIUMCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/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/M
EPSS: 0.35% probability · 29th percentile
Public exploits: None in Exploit-DB
CISA KEV: Not listed
Weakness: CWE-400
Affected: vllm/vllm
Source: disclosure@vulncheck.com

EPSS trend

EPSS moved from 0.3% on 27 September 2026 to 0.4% on 27 October 2026.

References

https://github.com/vllm-project/vllm/security/advisories/GHSA-jcq2-4gch-5qhfVendor Advisory
https://www.vulncheck.com/advisories/vllm-before-0.29.0-uncontrolled-resource-consumption-via-audio-decodingThird Party Advisory

Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.