Low Risk

gdb_poll

Drain pending async GDB notifications. Args: timeout: Maximum time to wait (seconds) for the first event.

How to control gdb_poll ↓

AI agents call gdb_poll to retrieve information from Pwno without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool reads/queries the state of a debugger's event queue without modifying the debugger state, target process, or any data. It is purely observational—polling for and returning notifications that have already been generated. While it operates in a debugging context (GDB), the act itself is a non-destructive read of asynchronous events, making it Read category with low severity.

From the tool's definition The tool drains (retrieves) pending async GDB notifications with no ability to modify state, execute commands, or perform side effects.

Documented attack patterns abuse exactly the kind of access gdb_poll gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Pwno, and nothing reaches the server without passing your rules. This is the rule we recommend for gdb_poll:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "gdb_poll": {}
  }
}

gdb_poll is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Pwno — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the gdb_poll tool do? +

Drain pending async GDB notifications. Args: timeout: Maximum time to wait (seconds) for the first event. It is categorised as a Read tool in the Pwno MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on gdb_poll? +

Register the Pwno MCP server in PolicyLayer and add a rule for gdb_poll: 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 Pwno. Nothing to install.

What risk level is gdb_poll? +

gdb_poll is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit gdb_poll? +

Yes. Add a rate_limit block to the gdb_poll 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.

How do I block gdb_poll completely? +

Set action: deny in the PolicyLayer policy for gdb_poll. 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.

What MCP server provides gdb_poll? +

gdb_poll is provided by the Pwno MCP server (pwno-io/pwno-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pwno tool call.

Deterministic rules across all 36 Pwno tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

36 Pwno tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.