Real Skill packageSource verifiedClawHub registry

remote-macos-computer-use

Set up and use cua-driver (an MCP server) so an AI agent running on a remote/cloud host can drive a macOS desktop, with a persistent background daemon + reverse-SSH-tunnel wiring that survives reboots and stays in the background. Use when you want an agent on server A to click/type/capture on a Mac on another network, or to onboard a remote desktop onto any MCP-capable agent (Hermes, Claude Code, Codex, Cursor, OpenCode). Covers install, macOS TCC grants, remote login, reverse tunnel, per-agent MCP config, health…

Identity and source

Publisher attribution东海大鲨鱼(DSBS)registry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 58% rule confidence
Package forminstruction with code12 recorded files
Canonical sourceClawHub registryclawhub:dont-see-big-shark:remote-macos-computer-use
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/30/2026.claude/skills/remote-macos-computer-use

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/30/2026.agents/skills/remote-macos-computer-use

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/30/2026skills/remote-macos-computer-use

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @dont-see-big-shark/remote-macos-computer-use
clawhub inspect @dont-see-big-shark/remote-macos-computer-use --version 0.1.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
7 / 12 inspected as text
Checked
8/30/2026, 4:44:55 PM
Scanner
0.1.3
Policy
1.0.3
6 automated findings
highInstructions or code access sensitive credential locationsSKILL.md:57 · confidence 85%~/.ssh/id_ed25519_mac
highInstructions or code access sensitive credential locationsscripts/gen-mcp-config.py:8 · confidence 85%~/.ssh/id_ed25519_mac
highInstructions or code access sensitive credential locationsREADME.md:72 · confidence 85%~/.ssh/id_ed25519_mac
mediumRemote installer is downloaded without an integrity checkSKILL.md:32 · confidence 70%curl -fsSL https://cua.ai/driver/install.sh
mediumRemote installer is downloaded without an integrity checkscripts/setup-mac.sh:30 · confidence 70%curl -fsSL https://cua.ai/driver/install.sh
mediumRemote installer is downloaded without an integrity checkREADME.md:58 · confidence 70%curl -fsSL https://cua.ai/driver/install.sh
3 High/Critical review queue entries
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
Open human review queue →
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
6 dependency and API indicators
  • api: clawhub.ai
  • api: cua.ai
  • api: github.com
  • api: img.shields.io
  • api: raw.githubusercontent.com
  • api: www.apple.com
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/30/2026, 3:44:54 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:ce6069b4efb63f0b315fa0d32a844d23b31419ad1d9a1962187c2db3845894dd
Show up to 12 recorded paths
  • README.md
  • scripts
  • scripts/doctor-mac.sh
  • scripts/gen-mcp-config.py
  • scripts/setup-mac.sh
  • skill-card.md
  • SKILL.md
  • templates
  • templates/com.remote-macos.keep-awake.plist
  • templates/com.remote-macos.tunnel.plist
  • templates/com.trycua.driver.plist
  • templates/tunnel.sh

Source changelog

Initial release: Enables remote macOS desktop control by a remote AI agent using cua-driver MCP, with persistent daemon and reverse-SSH tunnel setup. - Full onboarding guide: install cua-driver, grant macOS permissions, set up SSH, and background persistence. - Automated setup script for persistent daemon, reverse tunnel, and keep-awake logic via LaunchAgents. - Step-by-step integration with agent frameworks (Hermes, Claude Code, Codex, etc.). - Health checks, troubleshooting steps, and safety considerations included. - Bounded (safety) mode and per-agent MCP config supported.