CVE-2026-57173
Received
Received - Intake
BaseFortify
Vulnerability report for CVE-2026-57173, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.
Publication date: 2026-09-16
Last updated on: 2026-09-18
Assigner: GitHub, Inc.
Description
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 Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
Currently, no data is known.
Helpful Resources
Exploitability
CWE
KEV
| CWE ID | Description |
|---|---|
| CWE-770 | The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated. |
