Execute an existing Python script within the shared environment. Args: script_path: Path to the script. Use a container-visible path under /workspace; relative paths resolve under /workspace. args: Space-separated args for the script. cwd: Working directory (default /workspace). Use a container-v...
AI agents invoke execute_python_script 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 runs Python code with user-controlled arguments and working directory in a shared environment. Combined with the server's debugging/binary research context (GDB, pwndbg, exploit workflows), it can execute arbitrary scripts that modify system state, read sensitive data, or trigger external operations. The ability to specify args and cwd makes it highly exploitable.
From the tool's definition Tool description explicitly states 'Execute an existing Python script within the shared environment' and accepts arbitrary `args` and `cwd` parameters, enabling execution of arbitrary code with configurable working directory and timeout control.
Documented attack patterns abuse exactly the kind of access execute_python_script 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 execute_python_script:
{
"version": "1",
"default": "deny",
"tools": {
"execute_python_script": {
"limits": [
{
"counter": "execute_python_script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_python_script 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 an existing Python script within the shared environment. Args: script_path: Path to the script. Use a container-visible path under /workspace; relative paths resolve under /workspace. args: Space-separated args for the script. cwd: Working directory (default /workspace). Use a container-visible path under /workspace; relative paths resolve under /workspace. timeout: Seconds to wait before termination. 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 execute_python_script: 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.
execute_python_script 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 execute_python_script 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 execute_python_script. 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.
execute_python_script 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.