vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference worker with a single request. The worker will remain down until it is restarted. Version 0.9.0 fixes the issue.
The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.
| Link | Tags |
|---|---|
| https://github.com/vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65 | exploit vendor advisory |
| https://github.com/vllm-project/vllm/pull/17623 | issue tracking vendor advisory |