remote-mac

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses various shell commands for network discovery and remote management of the author's infrastructure.
  • Executes tailscale status, dns-sd, and arp for discovering available hosts on the network.
  • Uses ssh with specific flags (-o RequestTTY=no -o RemoteCommand=none) to execute one-shot commands on remote machines such as steipete-macstudio.local and clawmac.
  • Monitors system and service health using tmux list-sessions, ps axww, lsof, and launchctl list on both local and remote hosts.
  • [SAFE]: The skill is designed for the management of the author's own infrastructure and incorporates explicit safety constraints.
  • Instructs the agent not to print secrets from remote files or shell environments.
  • Requires the agent to verify host identity and not assume identity from stale IP addresses.
  • Restricts the agent from installing, starting, or stopping services unless explicitly requested by the user, adhering to the principle of least intervention.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 06:37 AM