CVE-2026-73555 | vllm-project vLLM up to 0.25.x OpenAI Entrypoints server_utils.py validation_exception_handler/sanitize_message information disclosure

A vulnerability was found in vllm-project vLLM up to 0.25.x. It has been declared as problematic. This impacts the function validation_exception_handler/sanitize_message of the file vllm/entrypoints/openai/server_utils.py of the component OpenAI Entrypoints. The manipulation results in information disclosure.

This vulnerability is known as CVE-2026-73555. It is possible to launch the attack remotely. No exploit is available.

It is recommended to upgrade the affected component.VulDB Recent EntriesRead More