{"id":"CVE-2025-63603","details":"A command injection vulnerability exists in the MCP Data Science Server's (reading-plus-ai/mcp-server-data-exploration) 0.1.6 in the safe_eval() function (src/mcp_server_ds/server.py:108). The function uses Python's exec() to execute user-supplied scripts but fails to restrict the __builtins__ dictionary in the globals parameter. When __builtins__ is not explicitly defined, Python automatically provides access to all built-in functions including __import__, exec, eval, and open. This allows an attacker to execute arbitrary Python code with full system privileges, leading to complete system compromise. The vulnerability can be exploited by submitting a malicious script to the run_script tool, requiring no authentication or special privileges.","modified":"2026-03-13T03:40:50.528279Z","published":"2025-11-18T16:15:45.833Z","references":[{"type":"REPORT","url":"https://github.com/reading-plus-ai/mcp-server-data-exploration/issues/12"}],"affected":[{"database_specific":{"unresolved_ranges":[{"events":[{"introduced":"0"},{"last_affected":"0.1.6"}]}],"source":"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-63603.json"}}],"schema_version":"1.7.3","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N"}]}