Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-57173— vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM 是一个用于大语言模型的推理和服务引擎。在 0.24.0 版本之前，/v1/chat/completions 接口在处理 input_audio 参数时，调用 AudioMediaIO.load_bytes 或 AudioMediaIO.load_file 方法时，未将 VLLM_MAX_AUDIO_DECODE_DURATION_S 参数传递给共享的音频解码器。因此，未认证的攻击者可以提交一个体积较小的压缩音频输入，使其在解码后展开为极其庞大的 float32 格式 PCM 内存分配，从而绕过 /v1/a

CVSS 6.5 · Medium
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-57173

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
不加限制或调节的资源分配
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm < 0.24.0 -

II. Public POCs for CVE-2026-57173

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-57173

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-57173 (2)

Other References for CVE-2026-57173 (2)

Same Patch Batch · vllm-project · 2026-09-16 · 4 CVEs total

CVE-2026-69147 6.5 MEDIUM vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation
CVE-2026-92220 5.3 MEDIUM vllm-project vLLM MoRIIO Acknowledgement moriio_connector.py MoRIIOWrapper._handle_release
CVE-2026-92365 4.3 MEDIUM vllm-project vllm thinking_budget_state.py algorithmic complexity

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-770

V. Comments for CVE-2026-57173

No comments yet

Leave a comment