AI agents call devbox_list_dir to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries directory contents without modifying, deleting, or executing anything. It has no side effects and is purely informational. While the homelab context suggests elevated privileges, the tool itself is constrained to listing operations. Severity is low because directory enumeration alone poses minimal risk compared to tools that can execute code or modify systems.
From the tool's definition Tool name 'devbox_list_dir' and description 'List directory contents on the devbox (ls -la)' indicate a read-only directory listing operation equivalent to the Unix 'ls -la' command.
Attacks that exploit this kind of access
List directory contents on the devbox (ls -la). It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for devbox_list_dir: 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 Homelab. Nothing to install.
devbox_list_dir 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 devbox_list_dir 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 devbox_list_dir. 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.
devbox_list_dir is provided by the Homelab MCP server (nainounen/homelab-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 →