Lucene search
+L

6 matches found

PyPA
PyPA
•added 2026/10/01 4:38 p.m.•15 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...

6.5CVSS6.1AI score0.00687EPSS
SaveExploits0References8Affected Software1
OSV
OSV
•added 2026/09/16 10:12 p.m.•13 views

GHSA-HCWQ-8WJF-3GCR 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...

6.5CVSS6.1AI score0.00687EPSS
SaveExploits0References6
Github Security Blog
Github Security Blog
•added 2026/09/16 10:12 p.m.•21 views

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...

6.5CVSS6.1AI score0.00687EPSS
SaveExploits0References6Affected Software1
Snyk
Snyk
•added 2026/09/16 7:32 p.m.•9 views

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling through the inputaudio processing path in /v1/chat/completions. An attacker can cause excessive...

6.9CVSS5.8AI score0.00687EPSS
SaveExploits0References2
NVD
NVD
•added 2026/09/16 5:17 p.m.•24 views

CVE-2026-57173

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the inputaudio handling path for /v1/chat/completions calls AudioMediaIO.loadbytes or AudioMediaIO.loadfile without passing VLLMMAXAUDIODECODEDURATIONS to the shared audio decoder. An unauthenticated client can...

6.5CVSS0.00687EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2026/09/16 4:34 p.m.•13 views

CVE-2026-57173 vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the inputaudio handling path for /v1/chat/completions calls AudioMediaIO.loadbytes or AudioMediaIO.loadfile without passing VLLMMAXAUDIODECODEDURATIONS to the shared audio decoder. An unauthenticated client can...

6.5CVSS5.9AI score0.00687EPSS
SaveExploits0References4
Rows per page
Query Builder