list_directory

What list_directory does on Cowork Bench

AI agents call list_directory to retrieve information from Cowork Bench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why list_directory is rated Low

This is a straightforward filesystem read operation. It lists directory contents and has no side effects. The only mild risk is potential information disclosure if sensitive file paths exist, but the tool itself performs no destructive, executable, or financial operations. Severity is low because directory listings are typically non-sensitive metadata.

From the tool's definition Tool description states 'Get a detailed listing of all files and directories in a specified path' — a pure query operation that retrieves directory contents without modifying, executing, or deleting anything.

Risk signalsBulk/mass operation — affects multiple targets

The rule that runs list_directory safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_directory, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_directory": {}
  }
}

Questions about list_directory