查询亚马逊已授权店铺列表。
AI agents call sellfox_seller_lists to retrieve information from Sellfox MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about authorized Amazon seller stores/accounts. While it is fundamentally a Read operation (queries data without modification), it has high severity because it accesses sensitive seller account and authorization data. Unauthorized or malicious queries could reveal business-critical information about seller accounts, inventory, and operations.
From the tool's definition Tool name 'sellfox_seller_lists' and description '查询亚马逊已授权店铺列表' (query authorized Amazon seller lists) indicate a query/retrieval operation. The description explicitly uses '查询' (query/search), which is a read operation with no side effects.
Attacks that exploit this kind of access
查询亚马逊已授权店铺列表。. It is categorised as a Read tool in the Sellfox MCP MCP Server, which means it retrieves data without modifying state.
Register the Sellfox MCP server in PolicyLayer and add a rule for sellfox_seller_lists: 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 Sellfox MCP. Nothing to install.
sellfox_seller_lists 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 sellfox_seller_lists 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 sellfox_seller_lists. 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.
sellfox_seller_lists is provided by the Sellfox MCP server (shuolol/sellfox-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 →