wasm_agent_create · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What wasm_agent_create does on Claude Flow

AI agents invoke wasm_agent_create to trigger actions in Claude Flow. 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_create needs a policy

This tool creates and runs WASM agents capable of executing code in a sandbox. While sandboxed, it explicitly supports 'untrusted code execution' and spawns active compute agents. The blast radius is high because misuse could execute malicious WASM payloads, exhaust resources, or be used as a stepping stone despite sandbox claims — sandboxes can have escape vulnerabilities.

From the tool's definition Create a sandboxed WASM agent with virtual filesystem... untrusted code execution, browser-side run, deterministic replay

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wasm_agent_create Rate-limited

wasm_agent_create 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_create": {
      "limits": [
        {
          "counter": "wasm_agent_create_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about wasm_agent_create

What does the wasm_agent_create tool do? +

Create a sandboxed WASM agent with virtual filesystem (no OS access). Optionally use a gallery template. 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 Claude Flow 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_create? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for wasm_agent_create: 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 Claude Flow. Nothing to install.

What risk level is wasm_agent_create? +

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

Can I rate-limit wasm_agent_create? +

Yes. Add a rate_limit block to the wasm_agent_create 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_create completely? +

Set action: deny in the PolicyLayer policy for wasm_agent_create. 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_create? +

wasm_agent_create is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.