Delete a task list from Microsoft To Do.
AI agents call task_lists_delete to permanently remove resources in Outpost — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion of a task list. Deletion cannot be undone without backup/recovery mechanisms outside the tool's control. Although the blast radius is somewhat contained (limited to the user's task lists rather than system-wide data), the destructive nature and potential for unintended data loss (e.g., if an AI agent deletes the wrong list due to misunderstanding) justifies the…
From the tool's definition Tool name contains 'delete' and description states 'Delete a task list from Microsoft To Do.' The action irreversibly removes data (a task list and its contents).
Attacks that exploit this kind of access
Delete a task list from Microsoft To Do. It is categorised as a Destructive tool in the Outpost MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Outpost MCP server in PolicyLayer and add a rule for task_lists_delete: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Outpost. Nothing to install.
task_lists_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the task_lists_delete rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for task_lists_delete. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
task_lists_delete is provided by the Outpost MCP server (signalclaude/outpost). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →