Execute a system command and wait for completion. Note: Use this for build and helper commands. Do not use this to run the target binary under analysis. Use set_file + run (or attach) for the target. Use execute_python_code instead of python -c. Use pwncli for interactive exploit-driver workflows...
AI agents invoke run_command 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 arbitrary shell commands with effects that depend entirely on the command argument provided by the AI agent. While the description suggests it's for 'build and helper commands' and advises against certain uses, it fundamentally permits execution of any system command without restrictions, including potentially destructive operations like rm -rf, network access, or privilege escalation.
From the tool's definition Tool description explicitly states 'Execute a system command and wait for completion' and accepts arbitrary 'Shell command to run' as input argument.
Documented attack patterns abuse exactly the kind of access run_command 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_command:
{
"version": "1",
"default": "deny",
"tools": {
"run_command": {
"limits": [
{
"counter": "run_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_command 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 system command and wait for completion. Note: Use this for build and helper commands. Do not use this to run the target binary under analysis. Use set_file + run (or attach) for the target. Use execute_python_code instead of python -c. Use pwncli for interactive exploit-driver workflows. Args: command: Shell command to run. cwd: Working directory (defaults to /workspace). Use a container-visible path under /workspace; relative paths resolve under /workspace. timeout: Timeout in seconds. Returns: JSON string with stdout/stderr/exit code. 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_command: 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_command 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_command 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_command. 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_command 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.