Medium severity6.5NVD Advisory· Published Jun 22, 2026· Updated Jun 24, 2026
CVE-2026-54233
CVE-2026-54233
Description
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | < 0.24.0 | 0.24.0 |
Affected products
6- osv-coords4 versionspkg:apk/chainguard/vllm-cuda-13.2pkg:apk/chainguard/vllm-openai-cuda-13.0pkg:apk/chainguard/tritonserver-backend-vllm-cuda-13.0pkg:apk/chainguard/vllm-openai-cuda-12.9
< 0.24.0-r0+ 3 more
- (no CPE)range: < 0.24.0-r0
- (no CPE)range: < 0.24.0-r1
- (no CPE)range: < 25.11-r12
- (no CPE)range: < 0.28.0-r0
Patches
Vulnerability mechanics
References
8- github.com/vllm-project/vllm/pull/44970nvdIssue TrackingPatchWEB
- github.com/advisories/GHSA-6pr9-rp53-2pmcghsaADVISORY
- github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmcnvdThird Party AdvisoryWEB
- nvd.nist.gov/vuln/detail/CVE-2026-54233ghsaADVISORY
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3404.yamlghsaWEB
- github.com/vllm-project/vllm/commit/1b1359c33269446f13c05da9a90c25174cbea590ghsaWEB
- github.com/vllm-project/vllm/releases/tag/v0.23.1rc0ghsaWEB
- pypi.org/project/vllmghsaWEB
News mentions
1- vLLM: Six CVEs Disclosed in 21 Hours — Critical Auth Bypass, Code Execution, and GPU Memory LeaksVypr Intelligence · Jun 17, 2026