AI agents call get_command_history to retrieve information from LuzzyTool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves previously executed command history from the current session—a pure read operation with no side effects. However, severity is elevated to 'medium' rather than 'low' because command history can expose sensitive operational details, credentials, file paths, or API calls that an adversary could exploit if leaked.
From the tool's definition Tool name 'get_command_history' and description explicitly state '【查询操作】获取...命令历史记录' (retrieval operation / get command history). The verb is 'get/retrieve', indicating a read-only query of historical data with no modification or execution.
Attacks that exploit this kind of access
【查询操作】获取当前会话中所有已执行的命令历史记录。. It is categorised as a Read tool in the LuzzyTool MCP Server, which means it retrieves data without modifying state.
Register the LuzzyTool MCP server in PolicyLayer and add a rule for get_command_history: 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 LuzzyTool. Nothing to install.
get_command_history 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 get_command_history 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 get_command_history. 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.
get_command_history is provided by the LuzzyTool MCP server (luzzymeow/luzzytool). 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 →