AI agents use update_task to create or update resources in RoadBoard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RoadBoard environment.
This tool modifies existing data (task metadata) but does not delete, destroy, or execute arbitrary code. The changes are reversible—fields can be updated again to previous values. Status changes are explicitly delegated to a separate tool (update_task_status), confirming this is a modification-only operation.
From the tool's definition Tool explicitly updates task fields: title, description, priority, phase, assignee, due date. Description states 'Update fields of an existing task', which is a reversible modification operation.
Attacks that exploit this kind of access
Update fields of an existing task (title, description, priority, phase, assignee, due date). Use update_task_status to change status. It is categorised as a Write tool in the RoadBoard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RoadBoard MCP server in PolicyLayer and add a rule for update_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 RoadBoard. Nothing to install.
update_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_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 update_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.
update_task is provided by the RoadBoard MCP server (maless88/roadboard). 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 →