AI agents call task_status to retrieve information from Willow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves task metadata and completion information without creating, modifying, deleting, or executing any operations. It is purely informational and has no side effects. The result depends on existing task state, not on arbitrary input execution. Therefore, it falls clearly under the Read category with low severity due to its non-destructive, non-operational nature.
From the tool's definition Tool description states 'Poll the status of a submitted Kart task by task_id. Returns status, result, and completion time.' The verb 'poll' and 'returns' indicate retrieval of task state information without modification or execution of tasks.
Attacks that exploit this kind of access
Poll the status of a submitted Kart task by task_id. Returns status, result, and completion time. It is categorised as a Read tool in the Willow MCP Server, which means it retrieves data without modifying state.
Register the Willow MCP server in PolicyLayer and add a rule for task_status: 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 Willow. Nothing to install.
task_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the task_status 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_status. 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_status is provided by the Willow MCP server (rudi193-cmd/willow-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 →