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.