AI agents use karea_unlink_resource_from_task to create or update resources in Karea — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Karea environment.
This tool unlinks (removes an association between) a resource and a task, but explicitly does not delete either entity. This is a reversible modification of relational data, making it a Write operation. Since no data is permanently destroyed and the link can be re-created, severity is low.
From the tool's definition 'Remove the link between a resource and a task. Does not delete either side.'
Attacks that exploit this kind of access
Remove the link between a resource and a task. Does not delete either side. It is categorised as a Write tool in the Karea MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Karea MCP server in PolicyLayer and add a rule for karea_unlink_resource_from_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 Karea. Nothing to install.
karea_unlink_resource_from_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 karea_unlink_resource_from_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 karea_unlink_resource_from_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.
karea_unlink_resource_from_task is provided by the Karea MCP server (starecz/karea-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 →