AI agents use horoshop_update_order_status to create or update resources in Horoshop — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Horoshop environment.
The tool modifies order status through the Horoshop e-commerce API. Status updates are Write operations as they change data state reversibly (status can be updated again). Severity is high because misuse could disrupt order fulfillment workflows, customer communications, and business operations, though the change is theoretically reversible.
From the tool's definition Tool name contains 'update' and description states it 'Updates an order status', indicating modification of existing order data. This is a reversible state change operation.
Attacks that exploit this kind of access
Updates an order status using the Horoshop API. It is categorised as a Write tool in the Horoshop MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Horoshop MCP server in PolicyLayer and add a rule for horoshop_update_order_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 Horoshop. Nothing to install.
horoshop_update_order_status 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 horoshop_update_order_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 horoshop_update_order_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.
horoshop_update_order_status is provided by the Horoshop MCP server (narkov/horoshop-mcp-server). 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 →