High-risk tools in MCP Sandbox
3 of the 7 tools in MCP Sandbox are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
execute_python_codeExecuteExecutes Python code in a sandbox and returns results with links to generated files. Parameters: sandbox_id (string) - The sandbox ID to use, code (string) - The Python code to ...
-
execute_terminal_commandExecuteExecutes a terminal command in the specified sandbox. Parameters: sandbox_id (string), command (string). Returns stdout, stderr, exit_code.
-
install_package_in_sandboxExecuteInstalls a Python package in the specified sandbox. Parameters: sandbox_id (string), package_name (string)
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.