Lucene search
+L

6 matches found

RedhatCVE
RedhatCVE
•added 2026/10/25 1:55 p.m.•2 views

CVE-2026-116175

A flaw was found in vLLM. This vulnerability allows a remote authenticated attacker to cause a Denial of Service DoS by exhausting system memory. The multimodal chat processing component fails to enforce duration limits when decompressing audio inputs. By submitting a chat completion request...

7.1CVSS5.8AI score
SaveExploits0References5
CVE
CVE
•added 2026/10/25 1:20 p.m.•6 views

CVE-2026-116175

The vLLM framework versions 0.19.0 through 0.24.0 are vulnerable to an Audio Decompression Bomb (CWE-409). The root cause is that the AudioMediaIO multimodal path calls load_audio without enforcing the max_duration_s decoded-duration limit. This allows authenticated attackers to submit small, hig...

7.1CVSS5.9AI score
SaveExploits0References2
osv_pysec
osv_pysec
•added 2026/10/01 4:38 p.m.•22 views

PYSEC-2026-4179 vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

Summary The audio decode-duration guard maxdurations, env VLLMMAXAUDIODECODEDURATIONS, default 600s that protects against audio decompression-bomb DoS is wired into only the speech-to-text path /v1/audio/transcriptions. The chat audio path /v1/chat/completions, inputaudio content parts calls the...

6.5CVSS6AI score0.0073EPSS
SaveExploits0References8
PyPA
PyPA
•added 2026/10/01 4:38 p.m.•22 views

vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

SummaryThe audio decode-duration guard maxdurations, env VLLMMAXAUDIODECODEDURATIONS, default 600s that protects against audio decompression-bomb DoS is wired into only the speech-to-text path /v1/audio/transcriptions. The chat audio path /v1/chat/completions, inputaudio content parts calls the...

6.5CVSS6AI score0.0073EPSS
SaveExploits0References8Affected Software1
Cvelist
Cvelist
•added 2026/06/22 10:10 p.m.•68 views

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...

6.5CVSS0.00422EPSS
SaveExploits0References2
CVE
CVE
•added 2026/06/22 10:10 p.m.•102 views

CVE-2026-54233

Affected software: vLLM (inference/serving engine). Vulnerability: decoding an audio file on the /v1/audio/transcriptions endpoint can cause extreme memory growth. A 25 MB OPUS upload decodes to about 14.9 GB of float32 PCM, because the audio decoder concatenates all frames in memory before retur...

6.5CVSS5.8AI score0.00422EPSS
SaveExploits0References2Affected Software1
Rows per page
Query Builder