mobilebox@r1
VERIFIEDPublisher claims: "Enables AI agents to create and drive cloud Android phones, reading each screen as a numbered element list and then tapping, typing, installing apps, and parking or deleting phones. It exposes 12 tools covering the phone lifecycle, app installs, device settings like locale and GPS, plus screen observation and batched actions." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is mobilebox@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 87/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.