High-risk tools in Todo for AI MCP Server
7 of the 244 tools in Todo for AI MCP Server 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
-
append_run_logsExecuteAppend log entries to a specific Agent run. Use this during execution to record progress, tool calls, decisions, and errors for later replay and debugging.
-
escalate_overdue_tasksExecuteTrigger priority auto-escalation for overdue tasks. Tasks past their due date that are not yet urgent will have their priority bumped one level (low→medium→high→urgent). Can be ...
-
handoff_taskExecuteHand off a task from its current Agent to another Agent. Cancels the active assignment (if any) and creates a fresh assignment + run for the target Agent, recording a handoff ev...
-
launch_workflowExecuteLaunch a new run of a workflow. Creates tasks for each step, assigns matching Agents, and starts entry-point steps (those with no dependencies).
-
pause_workflow_runExecutePause a running workflow. Already-running steps continue, but no new steps will be started until resumed.
-
retry_workflow_runExecuteRetry a failed workflow by resetting failed/skipped steps and re-advancing the DAG.
-
start_sandbox_executionExecuteStart a new sandboxed execution for an Agent. Freezes the policy snapshot and returns the execution record + policy envelope.
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.