Medium · CVSS 6.5CVE-2026-57173GHSA-HCWQ-8WJF-3GCR

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

Answer in brief

CVE-2026-57173 records a Medium severity (CVSS 6.5) vulnerability in vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic), vllm (pip). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Sep 16, 2026Updated Oct 7, 2026Source checked Oct 31, 2026First seen by HOL Sep 16, 2026Material review Oct 7, 2026

Upstream Advisory

Key facts

Risk: Medium · CVSS 6.5
Exploitation: Not marked as known exploited
Affected software: 3 mapped packages or products
Fix availability: Available

Why this deserves its current priority

CVSS is 6.5. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps vllm-project/vllm (generic), vllm (pip). Check affected ranges and fixed versions before updating.

Affected products and reported versions
Product	Affected versions	Fixed versions
cpe:2.3:a:vllm:vllm::::::::	Not reported	Not reported

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
vllm-project/vllmgeneric	<0.24.0	0.24.0
vllmpip	<=0.23.0	0.24.0

Recommended response

Check inventory. Check lockfiles and deployed manifests for vllm-project/vllm, vllm.
Review the reported fix. Update vllm-project/vllm to 0.24.0; vllm to 0.24.0 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

Published upstream
Sep 16, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Oct 7, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Sep 16, 2026

Sources and claim methodology

Upstream source 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.

Quoted source text, attributed separately from HOL analysis.

Affected scope and exposure questions

The current feed maps vllm-project/vllm (generic), vllm (pip). Check affected ranges and fixed versions before updating.

Affected products and reported versions
Product	Affected versions	Fixed versions
cpe:2.3:a:vllm:vllm::::::::	Not reported	Not reported

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
vllm-project/vllmgeneric	<0.24.0	0.24.0
vllmpip	<=0.23.0	0.24.0

Sources and claim methodology

Upstream source description

Quoted source text, attributed separately from HOL analysis.