AI agents call sku_full_status 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.
The tool performs data retrieval only (fetching quantity states), which is characteristic of Read operations. It has no capability to modify inventory, create/delete records, execute external commands, or trigger financial transactions. The blast radius of misuse is minimal—an agent could only retrieve inventory visibility information about a SKU.
From the tool's definition Tool description states it 'fetch[es] ALL 5 quantity states for a single SKU in parallel' — a retrieval operation with no modification, deletion, or side effects.
Attacks that exploit this kind of access
Composite: fetch ALL 5 quantity states for a single SKU 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 sku_full_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 Gobox. Nothing to install.
sku_full_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 sku_full_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 sku_full_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.
sku_full_status 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 →