Execute a stepping command (c, n, s, ni, si). Args: command: One of {c, n, s, ni, si} or their long forms. Returns: Dict with MI responses and state.
AI agents invoke step_control 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 triggers external operations (GDB stepping commands) whose observable effects depend on the debugged program's state and arguments. While not destructive or financial, it executes code control flow operations that affect a running process. In an agent context, misuse could cause unintended program termination, state corruption, or information disclosure from stepping into sensitive code paths.
From the tool's definition Tool executes stepping commands (c, n, s, ni, si) in GDB/pwndbg debugger context; these are control flow commands that deterministically progress program execution and alter runtime state.
Documented attack patterns abuse exactly the kind of access step_control 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 step_control:
{
"version": "1",
"default": "deny",
"tools": {
"step_control": {
"limits": [
{
"counter": "step_control_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}step_control 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.
Execute a stepping command (c, n, s, ni, si). Args: command: One of {c, n, s, ni, si} or their long forms. Returns: Dict with MI responses 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 step_control: 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.
step_control 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 step_control 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 step_control. 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.
step_control 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.