Skills/ClawHub/mac-control

mac-control@1.0.0

VERIFIED· install only

Publisher claims: "Control Mac via mouse/keyboard automation using cliclick and AppleScript. Use for clicking UI elements, taking screenshots, getting window bounds, handling c..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher easonc13 · publishing for 276 daysInstalls 2,669Last detonated 23 min ago
$clawhub install mac-control
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
6 of 6 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 88/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sfilesystemwrote ~/.clawdbot/mac-control-calibration.json
0.4sprocessexec /usr/bin/mkdir
0.4sprocessexec /usr/bin/dirname
0.4sprocessexec /opt/homebrew/bin/cliclick
0.4sprocessexec /usr/sbin/screencapture
0.4sprocessexec /usr/bin/tail
0.4sprocessexec /usr/bin/awk
0.4sprocessexec /usr/bin/cat
0.4sprocessexec /usr/bin/rm
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: Coordinates should be from the displayed image (e.g., 2000x1125 display of 3840x2160 screenshot)
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1:
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexec /usr/bin/mkdir
0.4sprocessexec /opt/homebrew/bin/cliclick
0.4sprocessexec /usr/bin/cut
0.4sprocessexec /usr/sbin/screencapture
0.4sprocessexec /usr/bin/tail
0.4sprocessexec /usr/bin/awk
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessexec /usr/bin/grep
0.5sprocessexec /usr/bin/head
0.5sprocessexec /usr/bin/sed
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessexited 127: ./scripts/get-window-bounds.sh: line 10: osascript: command not found
0.5sprocess6 of 6 bundled scripts run with no arguments
0.5sprocessscript backend runs setup only
0.5sprocessscript backend runs setup only
0.5sprocessno install scripts to re-run

Static findings

No findings across 696 lines in 8 files.

Cost to the agent

Instructions loaded
≈2,014 tok
1 file · 8 in bundle

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.