Delete a task. Auto-claims then releases after deletion.
AI agents call delete_task to permanently remove resources in Task — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Task deletion is a destructive action that permanently removes data from the task management system. Unlike write operations (create, update) which are reversible, deletion cannot be undone. This carries significant risk if an agent misuses it to delete important tasks.
From the tool's definition The tool explicitly 'Delete[s] a task' which irreversibly removes data. The description confirms it deletes the task after auto-claiming it, making this an unrecoverable operation that cannot be undone.
Attacks that exploit this kind of access
Delete a task. Auto-claims then releases after deletion. It is categorised as a Destructive tool in the Task MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Task MCP server in PolicyLayer and add a rule for delete_task: 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 Task. Nothing to install.
delete_task 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 delete_task 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 delete_task. 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.
delete_task is provided by the Task MCP server (maxronner/taskwarrior-mcp). 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 →