CVE-2026-57173
CVSS v3
6.5
MEDIUM
EPSS Score
0.7 %
exploit probability, as of 2026-10-12
CISA KEV
No
known exploited
Exploitation
—
SSVC status
Get an alert for each new CVE published for vllm. Watch vllm in CVE Watch Free account · no credit card
Affected and fixed versions
Packages from OSV.dev and products from the vendors' CSAF advisories.
version not verifiedVersions not verified: read as OSV.dev and the vendors publish them, not checked against each vendor's release list.
Packages
- vllmPyPIall versions · fixed in 0.24.0
Vendor advisories
vllm: vLLM: Denial of Service via unauthenticated audio decompression
rhaii/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server · rhaii/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server · rhaii/vllm-gaudi-rhel9 as a component of Red Hat AI Inference Server
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.
Technical details
- CVSS v3 Vector
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Published
- 2026-09-16
- Last Modified
- 2026-09-16
Frequently asked questions
What is CVE-2026-57173?
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.
Is CVE-2026-57173 actively exploited?
Active exploitation of CVE-2026-57173 has not been confirmed. Its EPSS score was 0.7% on 2026-10-12, the estimated probability of exploitation in the next 30 days.
What is the CVSS score for CVE-2026-57173?
CVE-2026-57173 has a CVSS v3 base score of 6.5 (MEDIUM severity), with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
Running vllm? Hear about its next vulnerability
CVE Watch matches each new CVE to the vendors and products you list (vendor and product, not the version) and puts it in your alerts with its KEV and EPSS status.
Already have an account? Open CVE Watch
No credit card required · 50 free checks/month · Free API key
Go further
- Following what attackers exploit right now? The CISA KEV additions of the month, with their patch deadlines.
- Running this software? CVE Watch alerts you to new vulnerabilities in your products.
Related vulnerabilities
Same product first, then the same vendor advisory and the same publication week.