AI agents call gobuster_wordlists to retrieve information from Gobuster without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only enumerates and returns available wordlist files from the Kali host. It has no side effects, cannot modify data, and cannot trigger scanning or external operations. The blast radius of misuse is minimal—an attacker gains only a listing of files that are already public/discoverable on the system.
From the tool's definition Tool name contains 'list' and description states 'List available wordlists' — a pure query operation that retrieves information without modifying or executing anything on the remote host.
Attacks that exploit this kind of access
List available wordlists on the Kali host. It is categorised as a Read tool in the Gobuster MCP Server, which means it retrieves data without modifying state.
Register the Gobuster MCP server in PolicyLayer and add a rule for gobuster_wordlists: 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 Gobuster. Nothing to install.
gobuster_wordlists 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 gobuster_wordlists 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 gobuster_wordlists. 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.
gobuster_wordlists is provided by the Gobuster MCP server (schwarztim/sec-gobuster-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 →