# bash

Run a host command (if enabled).

Agent View of the PolicyLayer registry record for `bash`. HTML page: https://policylayer.com/tools/openclaw/bash

## Facts

- Tool: `bash`
- Server: OpenClaw (`openclaw`) — https://policylayer.com/tools/openclaw.md
- Install: `npx -y openclaw`
- Homepage: https://www.npmjs.com/package/openclaw
- Risk category: Execute (High risk)
- Registry record: grade F, identity verified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "bash",
    "arguments": {}
  }
}
```

## Why bash is rated High

Running host commands is a quintessential Execute operation with maximal blast radius. An AI agent with access to bash can read files, modify system state, install malware, exfiltrate data, pivot to other systems, or destroy infrastructure—all depending on the arguments provided and the privilege level of the process. This warrants critical severity regardless of conditional language ('if enabled').

From the tool's own definition: "Tool description states 'Run a host command (if enabled)'. This directly invokes arbitrary shell commands on the host system."

## Use case

AI agents invoke bash to trigger actions in OpenClaw. 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches OpenClaw:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "bash": {
      "limits": [
        {
          "counter": "bash_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on OpenClaw (128)

- `drop` — Destructive — https://policylayer.com/tools/openclaw/drop.md
- `reset` — Destructive — https://policylayer.com/tools/openclaw/reset.md
- `uninstall` — Destructive — https://policylayer.com/tools/openclaw/uninstall.md
- `abort` — Execute — https://policylayer.com/tools/openclaw/abort.md
- `acp` — Execute — https://policylayer.com/tools/openclaw/acp.md
- `action` — Execute — https://policylayer.com/tools/openclaw/action.md
- `agent` — Execute — https://policylayer.com/tools/openclaw/agent.md
- `auth` — Execute — https://policylayer.com/tools/openclaw/auth.md
- `browser` — Execute — https://policylayer.com/tools/openclaw/browser.md
- `capability` — Execute — https://policylayer.com/tools/openclaw/capability.md
- `chat` — Execute — https://policylayer.com/tools/openclaw/chat.md
- `command` — Execute — https://policylayer.com/tools/openclaw/command.md
- `completion` — Execute — https://policylayer.com/tools/openclaw/completion.md
- `crestodian` — Execute — https://policylayer.com/tools/openclaw/crestodian.md
- `cron` — Execute — https://policylayer.com/tools/openclaw/cron.md
- `daemon` — Execute — https://policylayer.com/tools/openclaw/daemon.md
- `doctor` — Execute — https://policylayer.com/tools/openclaw/doctor.md
- `elevated` — Execute — https://policylayer.com/tools/openclaw/elevated.md
- `events_wait` — Execute — https://policylayer.com/tools/openclaw/events-wait.md
- `gateway` — Execute — https://policylayer.com/tools/openclaw/gateway.md
- `infer` — Execute — https://policylayer.com/tools/openclaw/infer.md
- `new` — Execute — https://policylayer.com/tools/openclaw/new.md
- `node` — Execute — https://policylayer.com/tools/openclaw/node.md
- `nodes` — Execute — https://policylayer.com/tools/openclaw/nodes.md
- `permissions_respond` — Execute — https://policylayer.com/tools/openclaw/permissions-respond.md
- `phone` — Execute — https://policylayer.com/tools/openclaw/phone.md
- `plugins` — Execute — https://policylayer.com/tools/openclaw/plugins.md
- `proxy` — Execute — https://policylayer.com/tools/openclaw/proxy.md
- `qa` — Execute — https://policylayer.com/tools/openclaw/qa.md
- `restart` — Execute — https://policylayer.com/tools/openclaw/restart.md
- …and 98 more: https://policylayer.com/tools/openclaw.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=openclaw · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/openclaw