execute_csharp
EXPERIMENTAL. Compile + run a C# snippet inside the s&box EDITOR (which is unsandboxed): writes a temp [ConCmd] into the project
This record as markdown: /tools/sbox/execute-csharp.md
What execute_csharp does on Sbox
AI agents invoke execute_csharp to trigger actions in Sbox. 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.
Why execute_csharp is rated High
This tool permits execution of arbitrary C# code within the s&box editor runtime without sandboxing constraints. The unsandboxed nature and ability to write ConCmd entries means an AI agent could execute malicious code with the full privileges of the editor process, potentially compromising the game project, the development environment, or the host system.
From the tool's definition Tool description states: "Compile + run a C# snippet inside the s&box EDITOR (which is unsandboxed)" — explicitly indicates arbitrary code execution in an unsandboxed environment with full editor access.
Attacks that exploit this kind of access
The rule that runs execute_csharp safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sbox, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For execute_csharp, this is the rule to start with:
execute_csharp 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Sbox, apply this rule, and every execute_csharp call is checked against it from then on.
Questions about execute_csharp
EXPERIMENTAL. Compile + run a C# snippet inside the s&box EDITOR (which is unsandboxed): writes a temp [ConCmd] into the project. It is categorised as a Execute tool in the Sbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sbox MCP server in PolicyLayer and add a rule for execute_csharp: 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 Sbox. Nothing to install.
execute_csharp 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_csharp 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_csharp. 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_csharp is provided by the Sbox MCP server (sbox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sbox, and thousands of servers like it.
This server
Across the catalogue