Lucene search
+L

9 matches found

NVD
NVD
•added 2026/09/12 1:16 p.m.•27 views

CVE-2026-90554

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 nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyavBytesIOvideobytes without the maxdurations or maxdecodebytes parameters, so neith...

7.5CVSS0.00201EPSS
SaveExploits0References2
RedhatCVE
RedhatCVE
•added 2026/09/12 12:29 p.m.•21 views

CVE-2026-90554

A flaw was found in vLLM. This vulnerability allows a remote attacker to cause a denial of service by providing a specially crafted, highly compressed video as multimodal input when the NanoNemotronVL model is configured to use audio from video. The lack of proper size or duration limits during...

7.5CVSS5.9AI score0.00201EPSS
SaveExploits0References5
EUVD
EUVD
•added 2026/09/12 12:08 p.m.•19 views

EUVD-2026-76872

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 nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyavBytesIOvideobytes without the maxdurations or maxdecodebytes parameters, so neith...

6.9CVSS5.7AI score0.00201EPSS
SaveExploits0References2
OSV
OSV
•added 2026/09/12 12:08 p.m.•14 views

CVE-2026-90554 vLLM before 0.28.0 Denial of Service via audio extraction

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 nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyavBytesIOvideobytes without the maxdurations or maxdecodebytes parameters, so neith...

6.9CVSS5.7AI score
SaveExploits0References4
CVE
CVE
•added 2026/09/12 12:08 p.m.•60 views

CVE-2026-90554

The vLLM inference engine (versions >=0.10.2 and

7.5CVSS5.8AI score0.00201EPSS
SaveExploits0References2Affected Software1
Cvelist
Cvelist
•added 2026/09/12 12:08 p.m.•48 views

CVE-2026-90554 vLLM before 0.28.0 Denial of Service via audio extraction

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 nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyavBytesIOvideobytes without the maxdurations or maxdecodebytes parameters, so neith...

6.9CVSS0.00201EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
•added 2026/09/12 12:08 p.m.•9 views

CVE-2026-90554 vLLM before 0.28.0 Denial of Service via audio extraction

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 nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyavBytesIOvideobytes without the maxdurations or maxdecodebytes parameters, so neith...

6.9CVSS5.8AI score0.00201EPSS
SaveExploits0References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/12 12:00 a.m.•2 views

CVE-2026-90554: Uncontrolled Resource Consumption

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 nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyavBytesIOvideobytes without the maxdurations or maxdecodebytes parameters, so neith...

7.5CVSS5.7AI score0.00201EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
•added 2026/09/12 12:00 a.m.•22 views

PT-2026-90659

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 pyavBytesIOvideo bytes without the max duration s or max decode bytes...

6.9CVSS5.7AI score0.00201EPSS
SaveExploits0References3
Rows per page
Query Builder