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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| vllm-project | vllm | < 0.23.1rc0 | — |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | vllm | < 0.24.0 | 0.24.0 | GHSA-6pr9-rp53-2pmc |
| PyPI | vllm | <= 0.23.0 | — | PYSEC-2026-3404 |
Advisories 1
- WID-SEC-2026-1897 vllm: Mehrere Schwachstellen BSI CERT-Bund (WID) · Oct 5, 2026