AI agents call search_all_orders to retrieve information from Gobox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves order data from the Gobox e-commerce platform without creating, modifying, or deleting anything. While it returns potentially sensitive business data (all orders), the impact is limited to information disclosure; an AI agent misusing this would at worst retrieve data it shouldn't see, not cause operational or financial damage. Therefore it is classified as Read with low severity.
From the tool's definition Tool description states "Fetch ALL orders across all pages in parallel" — the verb 'Fetch' indicates data retrieval with no modifications. The function name 'search_all_orders' also follows a read-only pattern (search/query operations).
Attacks that exploit this kind of access
Fetch ALL orders across all pages in parallel. It is categorised as a Read tool in the Gobox MCP Server, which means it retrieves data without modifying state.
Register the Gobox MCP server in PolicyLayer and add a rule for search_all_orders: 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 Gobox. Nothing to install.
search_all_orders 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 search_all_orders 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 search_all_orders. 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.
search_all_orders is provided by the Gobox MCP server (winter279/gobox-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 →