wasm_agent_tool · Ruflo MCP: Risk & Policy

WHAT IT DOES

What wasm_agent_tool does on Ruflo

AI agents invoke wasm_agent_tool to trigger actions in Ruflo. 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 IT NEEDS A POLICY

Why wasm_agent_tool needs a policy

This tool executes arbitrary code in a WASM sandbox environment. While sandboxing provides some isolation, it remains an Execute-category tool because: (1) it explicitly supports code execution via 'untrusted code execution' workflows, (2) the effects depend on what code/arguments are passed to it, (3) the blast radius is high if an agent misuses it to run malicious or unintended code.

From the tool's definition Tool description explicitly states 'Execute a tool on a WASM agent sandbox' and mentions 'untrusted code execution' as a primary use case.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wasm_agent_tool Rate-limited

wasm_agent_tool 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "wasm_agent_tool": {
      "limits": [
        {
          "counter": "wasm_agent_tool_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ruflo, so you can run agents against it safely.

FAQ

Questions about wasm_agent_tool

What does the wasm_agent_tool tool do? +

Execute a tool on a WASM agent sandbox. Tools: read_file, write_file, edit_file, write_todos, list_files. Use flat format: {tool, path, content, ...}. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, deterministic replay. Pair with wasm_gallery_search to find a published agent, or wasm_agent_create to scaffold a fresh one. For trusted in-process work, native Task is fine. It is categorised as a Execute tool in the Ruflo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wasm_agent_tool? +

Register the Ruflo MCP server in PolicyLayer and add a rule for wasm_agent_tool: 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 Ruflo. Nothing to install.

What risk level is wasm_agent_tool? +

wasm_agent_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit wasm_agent_tool? +

Yes. Add a rate_limit block to the wasm_agent_tool 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.

How do I block wasm_agent_tool completely? +

Set action: deny in the PolicyLayer policy for wasm_agent_tool. 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.

What MCP server provides wasm_agent_tool? +

wasm_agent_tool is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.