EUVD-2026-41914

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLMMAXAUDIOCLIPFILESIZEMB...

CVE-2026-54233

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. A remote attacker could exploit a vulnerability in the /v1/audio/transcriptions endpoint. By uploading a specially crafted compressed audio file, such as an OPUS file, the attacker could cause the system to...

CVE-2026-54233

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...

GHSA-6PR9-RP53-2PMC 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...

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...

PT-2026-50489

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.23.1rc0 Description The '/v1/audio/transcriptions' endpoint limits the size of compressed uploads but fails to limit the size of the decoded PCM Pulse Code Modulation output. PCM is an uncompressed digital audio format...

Summarize 代码问题漏洞

Summarize is a multi-source rapid summarization tool developed by Peter Steinberger. Versions of Summarize prior to 0.17.0 contained code vulnerabilities. These vulnerabilities were caused by server-side request forgeing attacks. Attackers could exploit these vulnerabilities by providing maliciou...

CVE-2026-25058

Vexa is an open-source, self-hostable meeting bot API and meeting transcription API. Prior to 0.10.0-260419-1910, the Vexa transcription-collector service exposes an internal endpoint GET /internal/transcripts/meetingid that returns transcript data for any meeting without any authentication or...

CVE-2026-45315

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.3, the audio transcription upload endpoint takes the file extension from the user-supplied filename and saves the file under CACHEDIR/audio/transcriptions/.. The /cache/path route serve...

CVE-2026-45315

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.3, the audio transcription upload endpoint takes the file extension from the user-supplied filename and saves the file under CACHEDIR/audio/transcriptions/.. The /cache/path route serve...

CVE-2026-45315 Open WebUI: Stored XSS via attacker-controlled file extension in /api/v1/audio/transcriptions

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.3, the audio transcription upload endpoint takes the file extension from the user-supplied filename and saves the file under CACHEDIR/audio/transcriptions/.. The /cache/path route serve...

EUVD-2026-30656

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.3, the audio transcription upload endpoint takes the file extension from the user-supplied filename and saves the file under CACHEDIR/audio/transcriptions/.. The /cache/path route serve...

CVE-2026-45315

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.3, the audio transcription upload endpoint takes the file extension from the user-supplied filename and saves the file under CACHEDIR/audio/transcriptions/.. The /cache/path route serve...

Open WebUI 跨站脚本漏洞

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI that is open source. Versions of Open WebUI prior to 0.9.3 had a cross-site scripting vulnerability. This vulnerability stemmed from the audio transcription upload endpoint, which extracted the file extension from the...

GHSA-M8F9-9WHG-F4XR Open WebUI has stored XSS via attacker-controlled file extension in /api/v1/audio/transcriptions

Summary The audio transcription upload endpoint takes the file extension from the user-supplied filename and saves the file under CACHEDIR/audio/transcriptions/.. The /cache/path route serves these files via FileResponse, which sets Content-Type from the on-disk extension and emits no...

Open WebUI has stored XSS via attacker-controlled file extension in /api/v1/audio/transcriptions

Summary The audio transcription upload endpoint takes the file extension from the user-supplied filename and saves the file under CACHEDIR/audio/transcriptions/.. The /cache/path route serves these files via FileResponse, which sets Content-Type from the on-disk extension and emits no...

CVE-2026-41374

OpenClaw before 2026.3.31 performs Discord audio preflight transcription before validating member authorization, allowing unauthenticated attackers to consume resources. Remote attackers can trigger audio preflight processing without member allowlist validation to cause resource exhaustion...

EUVD-2026-26083

OpenClaw before 2026.3.31 performs Discord audio preflight transcription before validating member authorization, allowing unauthenticated attackers to consume resources. Remote attackers can trigger audio preflight processing without member allowlist validation to cause resource exhaustion...

PT-2026-35759

OpenClaw before 2026.3.31 performs Discord audio preflight transcription before validating member authorization, allowing unauthenticated attackers to consume resources. Remote attackers can trigger audio preflight processing without member allowlist validation to cause resource exhaustion...

CVE-2026-41331

OpenClaw before 2026.3.31 contains a resource consumption vulnerability in Telegram audio preflight transcription that allows unauthorized group senders to trigger transcription processing. Attackers can exploit insufficient allowlist enforcement to cause resource or billing consumption by...