CVE-2026-100648: Uncontrolled Resource Consumption in vllm-project vllm
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.
AI Analysis
Technical Summary
The vllm-project's vllm software prior to version 0.29.0 does not properly enforce the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in its multimodal chat audio decoding functionality. This flaw enables unauthenticated attackers to bypass file size restrictions by submitting oversized audio files through chat endpoints, causing excessive consumption of memory and CPU resources during decoding.
Potential Impact
Attackers can exploit this vulnerability to cause denial of service conditions by consuming excessive system resources (memory and CPU) on the affected system. This can degrade performance or potentially crash the service handling the audio decoding, impacting availability.
Mitigation Recommendations
No official patch or remediation details are provided in the input data. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, consider restricting access to chat endpoints or implementing external file size validation controls to prevent oversized audio submissions.
CVE-2026-100648: Uncontrolled Resource Consumption in vllm-project vllm
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 v4.0
Score 6.9medium
Affected software
vllm-project
vllm
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vllm-project's vllm software prior to version 0.29.0 does not properly enforce the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in its multimodal chat audio decoding functionality. This flaw enables unauthenticated attackers to bypass file size restrictions by submitting oversized audio files through chat endpoints, causing excessive consumption of memory and CPU resources during decoding.
Potential Impact
Attackers can exploit this vulnerability to cause denial of service conditions by consuming excessive system resources (memory and CPU) on the affected system. This can degrade performance or potentially crash the service handling the audio decoding, impacting availability.
Mitigation Recommendations
No official patch or remediation details are provided in the input data. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, consider restricting access to chat endpoints or implementing external file size validation controls to prevent oversized audio submissions.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-09-26T02:33:07.898Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6ab7c9a7f7a7c5410652fd30
Added to database: 09/26/2026, 13:33:27 UTC
Last enriched: 09/26/2026, 14:03:31 UTC
Last updated: 09/27/2026, 04:31:31 UTC
Views: 12
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.