wasm_agent_prompt · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What wasm_agent_prompt does on Claude Flow

AI agents invoke wasm_agent_prompt 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_prompt needs a policy

This tool executes code in a WASM sandbox based on user prompts. The description explicitly mentions 'untrusted code execution' and 'browser-side run', indicating it triggers external computational operations whose effects depend on the prompt argument. While sandboxing mitigates risk compared to native execution, this remains code execution (Execute category).

From the tool's definition Send a prompt to a WASM agent and get a response. Use when native Task is wrong because the workload needs sandboxed isolation — untrusted code execution, browser-side run, deterministic replay.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wasm_agent_prompt Rate-limited

wasm_agent_prompt 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_prompt": {
      "limits": [
        {
          "counter": "wasm_agent_prompt_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_prompt

What does the wasm_agent_prompt tool do? +

Send a prompt to a WASM agent and get a response. 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_prompt? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for wasm_agent_prompt: 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_prompt? +

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

Can I rate-limit wasm_agent_prompt? +

Yes. Add a rate_limit block to the wasm_agent_prompt 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_prompt completely? +

Set action: deny in the PolicyLayer policy for wasm_agent_prompt. 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_prompt? +

wasm_agent_prompt 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.