Execute Python code dynamically in the shared environment. Args: code: Python source code to run. cwd: Working directory (default /workspace). If provided, use a container-visible path under /workspace; relative paths resolve under /workspace. timeout: Seconds to wait before termination. Prefer t...
AI agents invoke execute_python_code 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 allows execution of arbitrary Python code with full control over the execution environment (working directory, timeout). While the description notes it's intended for 'quick probes and analysis', the capability to execute any Python code in a shared environment presents critical risk of unauthorized code execution, data exfiltration, lateral movement, or system compromise.
From the tool's definition Tool executes arbitrary Python code dynamically with customizable working directory and timeout. Description explicitly states 'Execute Python code dynamically in the shared environment.'
Documented attack patterns abuse exactly the kind of access execute_python_code 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_code:
{
"version": "1",
"default": "deny",
"tools": {
"execute_python_code": {
"limits": [
{
"counter": "execute_python_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_python_code 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 Python code dynamically in the shared environment. Args: code: Python source code to run. cwd: Working directory (default /workspace). If provided, use a container-visible path under /workspace; relative paths resolve under /workspace. timeout: Seconds to wait before termination. Prefer this for quick probes and analysis, and only persist files in /workspace when the user explicitly asks. 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_code: 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_code 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_code 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_code. 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_code 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.