High-risk tools in LLDB-MCP
14 of the 28 tools in LLDB-MCP 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
-
lldb_commandExecuteExecute an LLDB command
-
lldb_finishExecuteExecute until the current function returns
-
lldb_runExecuteRun the loaded program
-
lldb_startExecuteStart a new LLDB session
-
lldb_continueExecuteContinue program execution
-
lldb_expressionExecuteEvaluate an expression in the current frame
-
lldb_loadExecuteLoad a program into LLDB
-
lldb_load_coreExecuteLoad a core dump file
-
lldb_nextExecuteStep over function calls
-
lldb_printExecutePrint value of expression
-
lldb_stepExecuteStep program execution
-
lldb_attachExecuteAttach to a running process
-
lldb_thread_selectExecuteSelect a specific thread
-
lldb_watchpointExecuteSet a watchpoint on a variable or memory address
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.