CVE-2026-100648

vllm before 0.29.0 fails to enforce VLLMMAXAUDIOCLIPFILESIZEMB 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 decodin...

EUVD-2026-87742

vllm before 0.29.0 fails to enforce VLLMMAXAUDIOCLIPFILESIZEMB 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 decodin...

CVE-2026-100648 vllm before 0.29.0 Uncontrolled Resource Consumption via Audio Decoding

vllm before 0.29.0 fails to enforce VLLMMAXAUDIOCLIPFILESIZEMB 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 decodin...

CVE-2026-100648 vllm before 0.29.0 Uncontrolled Resource Consumption via Audio Decoding

vllm before 0.29.0 fails to enforce VLLMMAXAUDIOCLIPFILESIZEMB 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 decodin...

CVE-2026-100648

Versions of vllm prior to 0.29.0 are vulnerable to a flaw where the software fails to enforce the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit during multimodal chat audio decoding. This allows unauthenticated remote attackers to bypass file size restrictions and submit oversized audio files through cha...

CVE-2026-100648 vllm before 0.29.0 Uncontrolled Resource Consumption via Audio Decoding

vllm before 0.29.0 fails to enforce VLLMMAXAUDIOCLIPFILESIZEMB 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 decodin...

CVE-2026-100648: Uncontrolled Resource Consumption

vllm before 0.29.0 fails to enforce VLLMMAXAUDIOCLIPFILESIZEMB 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 decodin...

Astra Linux – Vulnerability in libsdl1.2, libsdl2

SDL Simple DirectMediaLayer from version 1.2.15 to 2.x, and from 2.0.9 to 2.0.9, has a heap-based buffer overflow issue in the MSADPCMDecode function within audio/SDLwave.c...

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...

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...

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...

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...

CVE-2026-63633

A flaw was found in FreeRDP, a free implementation of the Remote Desktop Protocol. A malicious Remote Desktop Protocol RDP server can exploit a heap buffer overflow vulnerability during Opus audio decoding. This occurs when the server negotiates Opus audio with a vulnerable client, causing the...

ANT-2026-NGTJ413W · ffmpeg · heap-buffer-overflow

heap-buffer-overflow high Severity Claude high · Security research firm high · Maintainer - Discovered by Claude Mythos Preview REPORT Anthropic's analysis, sealed at approval. Disclosure to the maintainer was performed by Ada Logics. ANT-2026-NGTJ413W: This is a genuine heap-buffer-overflow...

CVE-2026-64835

FFmpeg versions 4.4 through 8.1.2 contain an out-of-bounds memory access vulnerability in the ADX audio decoder within libavcodec/adxdec.c that allows attackers to trigger both out-of-bounds reads and writes by supplying a crafted ADX or AAX audio file with a mid-stream channel layout change. Whe...

vLLM: OOM Denial of Service via Audio Decompression Bomb

SummaryvLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to 14.9GB of float32 PCM at decode time. Tested on vLLM v0.19.0. DetailsSpeechToTextProcessor rejects uploads over VLLMMAXAUDIOCLIPFILESIZEMB default 25MB based on...

CVE-2026-54233 vLLM: OOM Denial of Service via Audio Decompression Bomb

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to 14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0...

vLLM: OOM Denial of Service via Audio Decompression Bomb

Summary vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to 14.9GB of float32 PCM at decode time. Tested on vLLM v0.19.0. Details SpeechToTextProcessor rejects uploads over VLLMMAXAUDIOCLIPFILESIZEMB default 25MB based on...

freerdp: FreeRDP: Denial of Service via crafted audio data in RDP

A flaw was found in FreeRDP, a free implementation of the Remote Desktop Protocol RDP. A remote attacker can exploit a sizet underflow vulnerability in the IMA-ADPCM and MS-ADPCM audio decoders by sending specially crafted audio data over the RDPSND audio channel. This underflow leads to a...

freerdp: FreeRDP has a division-by-zero in ADPCM decoders when `nBlockAlign` is 0

A division by zero flaw has been discovered in FreeRDP. This division by zero exists in the MS-ADPCM and IMA-ADPCM decoders when nBlockAlign is 0, leading to a crash. In libfreerdp/codec/dsp.c, both ADPCM decoders use size % blocksize where blocksize = context-common.format.nBlockAlign. The...