What is GHSA-526f-298v-f597?

GHSA-526f-298v-f597 is a security advisory published by GitHub Security Advisories with Medium severity. vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat...

Which CVE IDs does GHSA-526f-298v-f597 cover?

GHSA-526f-298v-f597 covers the following CVE IDs: CVE-2026-100648. Each CVE has its own detail page on EchelonGraph Pulse with the synthesized EG score.

What is the CVSS v3 score of GHSA-526f-298v-f597?

GHSA-526f-298v-f597 has a CVSS v3 base score of 5.3, published by GitHub Security Advisories.

GHSA-526f-298v-f597MediumCVSS 5.3

vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat...

Vendor

GitHub Security Advisories

Published

September 26, 2026

Last Modified

September 26, 2026

🔗 CVE IDs covered (1)

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.

🔗 References (4)

https://github.com/vllm-project/vllm/security/advisories/GHSA-jcq2-4gch-5qhf
https://nvd.nist.gov/vuln/detail/CVE-2026-100648
https://www.vulncheck.com/advisories/vllm-before-0.29.0-uncontrolled-resource-consumption-via-audio-decoding
https://github.com/advisories/GHSA-526f-298v-f597