WRITE. Removes a reference (by url) from a task\
AI agents call remove_task_reference to permanently remove resources in Agentic Task System — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a reference from a task is an irreversible deletion of that association. Unlike an update or modification, once a reference is removed there is no built-in undo indicated. The blast radius is medium since it only affects a single reference link on a task rather than the task itself, but the action is not reversible by nature.
From the tool's definition 'Removes a reference (by url) from a task' — the word 'removes' indicates deletion of a task reference
Attacks that exploit this kind of access
WRITE. Removes a reference (by url) from a task\. It is categorised as a Destructive tool in the Agentic Task System MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agentic Task System MCP server in PolicyLayer and add a rule for remove_task_reference: 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 Agentic Task System. Nothing to install.
remove_task_reference 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 remove_task_reference 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 remove_task_reference. 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.
remove_task_reference is provided by the Agentic Task System MCP server (renezander030/agentic-task-system). 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 →