Incomplete Comparison with Missing Factors Affecting vllm package, versions [0.7.0,0.9.0)
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-10300988
- published4 Jun 2025
- disclosed28 May 2025
- creditKexin Oh
Introduced: 28 May 2025
NewCVE-2025-46722 (opens in a new tab)How to fix?
Upgrade vllm to version 0.9.0 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 Incomplete Comparison with Missing Factors due to the implementation of image hashing in hasher.py. An attacker can achieve hash collisions and potentially access or manipulate cached data by constructing images with identical pixel data but differing metadata, such as size or color mode.