Improper Handling of Highly Compressed Data (Data Amplification)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Handling of Highly Compressed Data Data Amplification via the AudioMediaIO multimodal path, which calls loadaudio without passing a...

CVE-2026-116175

vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls loadaudio without the maxdurations decoded-duration limit. Authenticated attackers can send small compressed audio via inputaudio or audiourl in /v1/chat/completions requests...

CVE-2026-116175 vLLM 0.19.0 before 0.24.0 Audio Decompression Bomb DoS via Chat Completions

vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls loadaudio without the maxdurations decoded-duration limit. Authenticated attackers can send small compressed audio via inputaudio or audiourl in /v1/chat/completions requests...

EUVD-2026-109436

vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls loadaudio without the maxdurations decoded-duration limit. Authenticated attackers can send small compressed audio via inputaudio or audiourl in /v1/chat/completions requests...

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...

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...

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...

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...

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...

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...