Description
vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.
Published: 2026-09-16
Score: 6.5 Medium
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-hcwq-8wjf-3gcr vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
History

Fri, 18 Sep 2026 04:15:00 +0000

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm

Thu, 17 Sep 2026 12:15:00 +0000

Type Values Removed Values Added
References
Metrics threat_severity

None

threat_severity

Moderate


Wed, 16 Sep 2026 16:45:00 +0000

Type Values Removed Values Added
Description vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.
Title vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
Weaknesses CWE-770
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}


Subscriptions

Vllm-project Vllm
cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-09-16T16:34:39.144Z

Reserved: 2026-06-24T01:47:55.285Z

Link: CVE-2026-57173

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-09-16T17:17:24.603

Modified: 2026-09-16T17:17:24.603

Link: CVE-2026-57173

cve-icon Redhat

Severity : Moderate

Publid Date: 2026-09-16T16:34:39Z

Links: CVE-2026-57173 - Bugzilla

cve-icon OpenCVE Enrichment

Updated: 2026-09-18T04:00:03Z

Weaknesses
  • CWE-770

    Allocation of Resources Without Limits or Throttling