SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityAnalyzed

CVE-2026-57173

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.

MEDIUM 6.5EPSS 0.73%

Does this matter?

Lower severity and a low EPSS score (0.73%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 3.1
6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.73% probability · 54th percentile
Public exploits
None in Exploit-DB
CISA KEV
Not listed
Weakness
CWE-770
Affected
vllm/vllm
Source
security-advisories@github.com
EPSS trend
0%3%5%27 October 2026: 0.73%27 October 202627 October 2026

EPSS 0.7% since 27 October 2026; no change recorded yet. Points are recorded when the score first appears and whenever it moves by a percentage point or more.

Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.