ClawHub

Mac Remote Access

v1.0.0

Diagnose, configure, and recover remote access to a macOS machine over Tailscale. Use when setting up or troubleshooting Mac SSH, Screen Sharing/VNC, RealVNC...

⭐ 0· 249·0 current·0 all-time
byliu liang@lliangcol
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (Mac remote access over Tailscale, SSH/VNC/AnyDesk/RustDesk) match the SKILL.md and reference files. No unrelated binaries, credentials, or config paths are requested.
✓
Instruction Scope
Runtime instructions are limited to local diagnostics and administrative actions (tailscale status/ip, netstat, nc, Test-NetConnection, restart screensharing). They do not direct data to external endpoints beyond standard remote-access tools. Note: several commands require sudo and will modify local services (e.g., kickstart screensharing), which is expected for this purpose.
✓
Install Mechanism
No install spec and no code files — instruction-only. The static scanner had no files needing code analysis.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. The included ACL template references typical Tailscale ACL fields but does not demand secrets from the user.
✓
Persistence & Privilege
always:false (default). The skill can be invoked autonomously (platform default) but does not request persistent system-wide privileges or modify other skills/configs.
Assessment
This skill appears coherent and focused on admin diagnostics. Before using it: (1) verify the skill author/source since the registry metadata has no homepage; (2) review any sudo commands you run and understand they will modify local services (restarting Screen Sharing is benign but disruptive); (3) when installing AnyDesk/RustDesk follow official vendor downloads and be cautious granting Accessibility/Screen Recording and unattended-access passwords; (4) avoid pasting sensitive outputs (logs, private keys, passwords) into public chat; and (5) if you plan to let the agent run autonomously, restrict that behavior or review suggested commands before execution.

Like a lobster shell, security has layers — review code before you run it.

latestvk97ag5hf0wgfdmef20bnet0czx82t039

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments