What’s Vulnerable › Vulnerabilities

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

• Severity: medium (CVSS 6.5 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.7% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-09-16 · updated 2026-10-07
• Weakness: CWE-770

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.

Affected products

• vllm-project vllm: before 0.24.0 — fixed in 0.24.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.24.0. Check the vendor advisory for mitigations.

References

• https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e
• https://github.com/vllm-project/vllm/pull/45908
• https://github.com/vllm-project/vllm/releases/tag/v0.24.0
• https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr

Get alerted when CVE-2026-57173 or the next vulnerability affects your stack