Run the loaded program under GDB control. Args: args: Argument string passed to the inferior. start: If True, stop at the program entry (equivalent to --start). Returns: MI run/continue results and state.
AI agents invoke run to trigger actions in Pwno. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a program (the 'inferior' process) under debugger control with user-supplied arguments, making it a direct Execute action. The blast radius is critical because: (1) it runs arbitrary loaded binaries, (2) arguments can be crafted to exploit or compromise the target, (3) in the context of a pwn framework, this enables exploit development and code execution attacks.
From the tool's definition Tool name 'run' with description 'Run the loaded program under GDB control' indicates execution of arbitrary binaries with attacker-controlled arguments ('args: Argument string passed to the inferior').
Documented attack patterns abuse exactly the kind of access run 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 run:
{
"version": "1",
"default": "deny",
"tools": {
"run": {
"limits": [
{
"counter": "run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run the loaded program under GDB control. Args: args: Argument string passed to the inferior. start: If True, stop at the program entry (equivalent to --start). Returns: MI run/continue results and state. It is categorised as a Execute tool in the Pwno MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pwno MCP server in PolicyLayer and add a rule for run: 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.
run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run 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 run. 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.
run 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.
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.