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.
References
| Link | Resource |
|---|---|
| https://github.com/vllm-project/vllm/pull/44970 | Issue Tracking Patch |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc | Third Party Advisory |
Configurations
History
No history.
Information
Published : 2026-06-22 23:16
Updated : 2026-06-24 16:52
NVD link : CVE-2026-54233
Mitre link : CVE-2026-54233
CVE.ORG link : CVE-2026-54233
JSON object : View
Products Affected
vllm
- vllm
CWE
CWE-409
Improper Handling of Highly Compressed Data (Data Amplification)
