Skills/ClawHub/computer-use-windows

computer-use-windows@0.1.1

CAUTION· install only

Publisher claims: "Top-level Windows computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules,..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wimi321 · publishing for 233 daysInstalls 3,033Last detonated 28 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 2 of 2 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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive file system command detected; Destructive command against a filesystem root or device. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexec /usr/bin/dirname
0.0sprocessexec /usr/bin/mkdir
0.0sprocessexited 127: ./scripts/install.sh: line 8: rsync: command not found
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ModuleNotFoundError: No module named 'winreg'
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: Node.js v22.23.5
0.2sprocess2 of 2 bundled scripts run with no arguments
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /usr/bin/mkdir
0.3sprocessexited 127: ./scripts/install.sh: line 8: rsync: command not found

Static findings

MEDIUM
Python subprocess execution detectedproject/runtime/windows_helper.py:446 · Python subprocess execution detectedos.startfile(target)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedproject/src/vendor/computer-use-mcp/toolCalls.ts:351 · Destructive file system command detected// clipboard holds `rm -rf /` — from the user, from a prior full-tier paste,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedproject/src/vendor/computer-use-mcp/types.ts:31 · Destructive file system command detected* Run button or scroll test output, but `type("rm -rf /")` is blockedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or deviceproject/src/vendor/computer-use-mcp/types.ts:31 · Destructive command against a filesystem root or device* Run button or scroll test output, but `type("rm -rf /")` is blockedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandproject/src/vendor/computer-use-mcp/types.ts:84 · Process kill command — agent can terminate processes* Independent kill switches for subtle/risky ported behaviors. Read fromFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandproject/src/vendor/computer-use-mcp/toolCalls.ts:3498 · Process kill command — agent can terminate processes// ─── Gate 1: kill switch ─────────────────────────────────────────────Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandproject/src/vendor/computer-use-mcp/types.ts:235 · Process kill command — agent can terminate processes/** The Settings-page kill switch (`chicagoEnabled` app preference). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedproject/runtime/windows_helper.py:452 · Python subprocess execution detectedsubprocess.Popen(["cmd", "/c", "start", "", target], shell=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedproject/runtime/windows_helper.py:450 · Python subprocess execution detectedsubprocess.Popen([resolved])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈554 tok
1 file · 45 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.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim wimi321: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim wimi321Propose a patch to the maintainer