Incorrect Type Conversion or Cast Affecting vllm package, versions [,0.30.0)
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-20877487
- published13 Oct 2026
- disclosed5 Oct 2026
- creditUnknown
Introduced: 5 Oct 2026
NewCVE-2026-105754 (opens in a new tab)How to fix?
Upgrade vllm to version 0.30.0 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 Incorrect Type Conversion or Cast via missing validation of multimodal data in the scale-out entrypoint's protocol.py before engine handoff. An authenticated remote attacker can send a GenerateRequest containing mm_placeholders with out-of-bounds offsets, overlapping ranges, or mismatched modality keys, causing the engine to crash.