CVE-2026-100648

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 Vector

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-jcq2-4gch-5qhf
• https://www.vulncheck.com/advisories/vllm-before-0.29.0-uncontrolled-resource-consumption-via-audio-decoding