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.
Severity (CVSS)
| Base score | 6.5 |
|---|---|
| Severity | Medium |
| Version | CVSS 3.1 |
| Vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| Provided by | CNA |
Weaknesses
- CWE-409 — CWE-409: Improper Handling of Highly Compressed Data (Data Amplification)
Affected products
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | < 0.23.1rc0 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc (x_refsource_CONFIRM)
- https://github.com/vllm-project/vllm/pull/44970 (x_refsource_MISC)
Generated from the official CVE List on 23 Jun 2026 10:05 UTC.