# skill_run

Run a tool exposed by an enabled skill in an isolated subprocess.

Agent View of the PolicyLayer registry record for `skill_run`. HTML page: https://policylayer.com/tools/yuga-hashimoto-localant/skill-run

## Facts

- Tool: `skill_run`
- Server: LocalAnt (`yuga-hashimoto/localant`) — https://policylayer.com/tools/yuga-hashimoto-localant.md
- Homepage: https://github.com/yuga-hashimoto/localant
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- 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": "skill_run",
    "arguments": {}
  }
}
```

## Why skill_run is rated High

This tool runs arbitrary enabled skills as subprocesses. While isolation mitigates some risk, execution of untrusted or misaligned skill code can trigger unintended side effects (file changes, network calls, installations, keystrokes).

From the tool's own definition: "'Run a tool exposed by an enabled skill in an isolated subprocess' — this directly executes code/tools in a subprocess, which is an execution primitive."

## Use case

AI agents invoke skill_run to trigger actions in LocalAnt. 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 LocalAnt:

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

## Other tools on LocalAnt (215)

- `adb_clear_logcat` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/adb-clear-logcat.md
- `adb_uninstall` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/adb-uninstall.md
- `fs_delete_file_with_approval` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/fs-delete-file-with-approval.md
- `git_reset` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/git-reset.md
- `git_reset_hard` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/git-reset-hard.md
- `git_restore_file` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/git-restore-file.md
- `mcp_server_unregister` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/mcp-server-unregister.md
- `secret_remove` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/secret-remove.md
- `shell_remove_allowed_command` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/shell-remove-allowed-command.md
- `skill_uninstall` — Destructive — https://policylayer.com/tools/yuga-hashimoto-localant/skill-uninstall.md
- `adb_input_text` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-input-text.md
- `adb_install_apk` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-install-apk.md
- `adb_keyevent` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-keyevent.md
- `adb_shell` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-shell.md
- `adb_start_app` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-start-app.md
- `adb_stop_app` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-stop-app.md
- `adb_swipe` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-swipe.md
- `adb_tap` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/adb-tap.md
- `agent_run` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/agent-run.md
- `approval_approve` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/approval-approve.md
- `autopilot` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/autopilot.md
- `bash` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/bash.md
- `browser_click` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-click.md
- `browser_close` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-close.md
- `browser_evaluate` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-evaluate.md
- `browser_open` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-open.md
- `browser_press` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-press.md
- `browser_scroll` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-scroll.md
- `browser_select` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-select.md
- `browser_type` — Execute — https://policylayer.com/tools/yuga-hashimoto-localant/browser-type.md
- …and 185 more: https://policylayer.com/tools/yuga-hashimoto-localant.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=yuga-hashimoto-localant · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/yuga-hashimoto-localant