A critical vulnerability (CVE-2024-3098) exists in the llama-index-core package versions prior to 0.10.24. It involves a prompt injection flaw in the safe_eval function of the exec_utils class, allowing attackers to bypass input validation and execute arbitrary code. This vulnerability is a bypass of a previously fixed issue (CVE-2023-39662) and has been demonstrated with a proof of concept that can create files on the affected system.