Improper Handling of Highly Compressed Data (Data Amplification) Affecting vllm package, versions [,0.28.0)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-VLLM-19784404
- published14 Sept 2026
- disclosed12 Sept 2026
- creditoran-s
Introduced: 12 Sep 2026
NewCVE-2026-90555 (opens in a new tab)How to fix?
Upgrade vllm to version 0.28.0 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Improper Handling of Highly Compressed Data (Data Amplification) in the transcription due to improper validation of audio sample rate headers. An attacker can cause excessive memory allocation and crash the API server by submitting forged FLAC headers with inflated sample rates.