Medium [CVE-2026-54233] Denial of Service via excessive memory allocation in audio transcription
This medium-severity Red Hat Linux advisory covers CVE-2026-54233 affecting Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI).
Aggregated and source-linked by VulniPulse. Data sources, validation and limitations.
VulniPulse record published Record updated
Summary
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output.
A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0.
A remote attacker could exploit a vulnerability in the `/v1/audio/transcriptions` endpoint. By uploading a specially crafted compressed audio file, such as an OPUS file, the attacker could cause the system to allocate an excessive amount of memory during the decoding process.
This uncontrolled memory allocation can lead to a Denial of Service (DoS) condition, making the service unavailable to legitimate users. Red Hat rates this issue as having Moderate impact.
A crafted audio upload to the vLLM /v1/audio/transcriptions endpoint can cause excessive decoded PCM allocation and denial of service. Affected components are vLLM serving images in Red Hat AI Inference Server, Red Hat OpenShift AI, and Red Hat Enterprise Linux AI bootc that ship vLLM prior to 0.23.1.
KServe sidecars are not affected. Red Hat severity: Moderate — CVSS 6.5 (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H).
Weakness: CWE-770. Red Hat lists Red Hat OpenShift AI (RHOAI) as not affected.
Red Hat does not currently list a fixing RHSA for this CVE.
Is CVE-2026-54233 exploited?
No exploitation is reported in the sources VulniPulse tracks: CVE-2026-54233 is not in the CISA KEV catalog (checked ) and this advisory does not report exploitation. That is not proof the vulnerability cannot be exploited.
How do I fix CVE-2026-54233?
Upgrade to a fixed release named by Red Hat:
- 0.23
Confirm against the vendor advisory before you patch.
- < 0.23.1rc0
Official advisory · high-confidence parse· fetched 14 days ago·verify at source
Mitigation checklist
- Limit access to audio transcription endpoints. Enforce authentication and request rate limits at the route or gateway. Set pod memory limits and restart policies. Upgrade to vLLM >= 0.23.1 when available from Red Hat.
Official advisory · high-confidence parse· fetched 14 days ago·verify at source
Get an email when Red Hat publishes the next one.
See Red Hat's last 90 days of advisories first. Then choose one product with live alerts free for life, or a free month of real-time alerts on everything with the severity, the fixed version and the vendor's link (card needed, then US$15/month; we email you before the first charge).
More Red Hat Linux advisories
- CVE-2026-48710May 26, 2026Security restriction bypass via malformed HTTP Host header
- CVE-2026-119977Oct 31, 2026Arbitrary code execution via predictable upgrade staging paths
- CVE-2026-111497Oct 22, 2026Out-of-Bounds Write in Google Brotli Decoder
- CVE-2026-109619Oct 21, 2026fatal error handling retains stale request state leading to use-after-free
- CVE-2026-109618Oct 21, 2026OOM bailout during request parsing leads to memory corruption and RCE
- CVE-2026-97229Oct 13, 2026integer overflow issue in CI/CD regular expression compiler
iPhone and Android apps · New on the App Store
Monitor future Red Hat Linux CVEs from your phone.
Choose a whole vendor or a precise platform, then receive matching security advisories by phone notification, email, or both. Coverage follows 34 official vendor sources and 160+ reviewed platform categories.
Discussion(0)
No comments yet. Share field notes, upgrade gotchas, or questions — verify against the vendor advisory before acting on community advice.
Sign in to join the discussion.