CVE-2026-57173
MEDIUMDescription
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.
How to fix
No published remediation has been found for this vulnerability's affected products yet.
Mitigation guidance may be in the linked vendor advisories in the References section below.
TridentStack Control tracks known vulnerabilities across your Windows, macOS, and Linux fleet and shows the fix as soon as one is published. See how it works
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Exploit Intelligence
EPSS data unavailable for this CVE.
References
Related Vulnerabilities
Other CWE-770 (Allocation of Resources Without Limits or Throttling) vulnerabilities, ordered by exploit likelihood. View all
| CVE | Severity | CVSS | EPSS | Exploited | Fix |
|---|---|---|---|---|---|
| CVE-2023-50387 | High | 7.5 | 100% | - | Fix |
| CVE-2019-11478 | Medium | 5.3 | 95% | - | Fix |
| CVE-2019-11479 | High | 7.5 | 92% | - | Fix |
| CVE-2024-27316 | High | 7.5 | 91% | - | Fix |
| CVE-2022-30522 | High | 7.5 | 90% | - | Fix |
| CVE-2019-9515 | High | 7.5 | 87% | - | Fix |
Common questions
How do I fix CVE-2026-57173?
No published fix for CVE-2026-57173 has been found yet. Check the linked vendor advisories for guidance as it becomes available.
How severe is CVE-2026-57173?
CVE-2026-57173 has a CVSS v3 base score of 6.5, rated medium. CVSS rates the technical impact if the vulnerability is exploited, not how likely that is, so weigh it alongside the exploit-prediction score when you decide what to patch first.
Embed a live status badge for CVE-2026-57173
Markdown
[](https://tridentstack.com/cve/CVE-2026-57173)HTML
<a href="https://tridentstack.com/cve/CVE-2026-57173"><img src="https://tridentstack.com/cve/badge/CVE-2026-57173.svg" alt="CVE-2026-57173"></a>Find and fix vulnerabilities across your fleet
TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.
This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-09-16.