AI agents call get_command_output to retrieve information from Kali Linux MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While the tool itself only reads/retrieves output (no side effects), the high severity reflects that in this penetration testing context, it will be used to exfiltrate results from dangerous operations. An agent could use execute_command to run destructive or financial attacks, then use get_command_output to steal the results.
From the tool's definition Tool name 'get_command_output' and description '获取交互式命令的最新输出' (retrieve latest output from interactive command) indicate retrieval of data with no direct side effects.
Documented attack patterns abuse exactly the kind of access get_command_output gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kali Linux MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_command_output:
{
"version": "1",
"default": "deny",
"tools": {
"get_command_output": {}
}
}get_command_output is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
获取交互式命令的最新输出。. It is categorised as a Read tool in the Kali Linux MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kali Linux MCP Server MCP server in PolicyLayer and add a rule for get_command_output: 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 Kali Linux MCP Server. Nothing to install.
get_command_output 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_output 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_output. 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_output is provided by the Kali Linux MCP Server MCP server (sfz009900/kalilinuxmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Kali Linux MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Kali Linux MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.