CVE-2025-71379 | vLLM up to 0.8.x OpenAI-compatible Serving Chat Endpoint vllm/lora/utils.py redos (GHSA-j828-28rj-hfhp)

A vulnerability labeled as problematic has been found in vLLM up to 0.8.x. Impacted is an unknown function of the file vllm/lora/utils.py of the component OpenAI-compatible Serving Chat Endpoint. The manipulation results in inefficient regular expression complexity.

This vulnerability is cataloged as CVE-2025-71379. The attack may be launched remotely. There is no exploit available.

The affected component should be upgraded.