Description (CNA)
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 (CNA)
| Vendor / product | Versions |
|---|---|
| vllm-project / vllm | affected < 0.23.1rc0 |
CWE
CWE-409
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc
- https://github.com/vllm-project/vllm/pull/44970
ADP enrichment
No English description supplied.
No references supplied.