Advisories

vLLM before 0.28.0 Denial of Service via audio extraction

Go Back
severity
medium
date
Affecting
  • vLLM >= 0.10.2, < 0.28.0

CWE
  • CWE-400 Uncontrolled Resource Consumption
CVSS
6.9
CVSS V4 Vector
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Credit
TobyB1702, jperezdealgaba
Description
vLLM versions >=0.10.2 and <0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nano_nemotron_vl.py, _extract_audio_from_videos calls load_audio_pyav(BytesIO(video_bytes)) without the max_duration_s or max_decode_bytes parameters, so neither VLLM_MAX_AUDIO_DECODE_DURATION_S nor VLLM_MAX_AUDIO_DECODE_BYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with use_audio_in_video=True, an attacker who supplies a small, highly compressed video as multimodal input can force the server to allocate gigabytes of memory during audio decoding, resulting in a denial of service. Fixed in vLLM 0.28.0.

Ready to get Started?

Explore VulnCheck, a next-generation Cyber Threat Intelligence platform, which provides exploit and vulnerability intelligence to help you prioritize and remediate vulnerabilities that matter.
  • Vulnerability Prioritization
    Prioritize vulnerabilities that matter based on the threat landscape and defer vulnerabilities that don't.
  • Early Warning System
    Real-time alerting of changes in the vulnerability landscape so that you can take action before the attacks start.