Skills/ClawHub/atl-mobile

atl-mobile@0.1.0

CAUTION· install only

Publisher claims: "Mobile browser and native app automation via ATL (iOS Simulator). Navigate, click, screenshot, and automate web and native app tasks on iPhone/iPad simulators." Observed in sandbox: calls github.com only, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jordancoin · publishing for 288 daysInstalls 3,171Last detonated 34 min ago

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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; install scripts ran; no agent task scenario for this bundle) on 2026-11-22 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: Host or command assembled from base64 fragments; Host or command assembled from base64 fragments; Host or command assembled from base64 fragments. Summary: calls github.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 6 s · 2 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
3.7sfilesystemread ~/Atl/.git/config · ~/Atl/.git/packed-refs · ~/Atl/.git/HEAD · ~/Atl/.git/refs/ · ~/Atl/.git/info/grafts · ~/Atl/.git/shallow outside project
3.7sfilesystemwrote ~/Atl/.git/description · ~/Atl/.git/info/exclude · ~/Atl/.git/hooks/pre-rebase.sample · ~/Atl/.git/hooks/pre-commit.sample · ~/Atl/.git/hooks/update.sample · ~/Atl/.git/hooks/post-update.sample
3.7snetworkCONNECT tcp://github.com:443
3.7sprocessexec /usr/bin/git
3.7sprocessexec /usr/lib/git-core/git
3.7sprocessexec /usr/lib/git-core/git-remote-https
3.7sprocessexec /usr/bin/grep
3.7sprocessexec /usr/bin/head
3.7sprocessexited 1: ./scripts/setup.sh: line 24: xcrun: command not found
3.7sprocessscript backend runs setup only
3.7sprocessscript backend runs setup only
5.6sprocesssecond launch, clock +45 days, CI unset
5.7sprocessexec /usr/bin/grep
5.7sprocessexec /usr/bin/head
5.7sprocessexited 1: ./scripts/setup.sh: line 24: xcrun: command not found

Static findings

HIGH
Host or command assembled from base64 fragmentsSKILL.md:647 · Host or command assembled from base64 fragments-d '{"id":"4","method":"screenshot","params":{}}' | jq -r '.result.data' | base64 -d > /tmp/page.pngFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Host or command assembled from base64 fragmentsSKILL.md:441 · Host or command assembled from base64 fragments-d '{"id":"3","method":"screenshot","params":{}}' | jq -r '.result.data' | base64 -d > screenshot.pngFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Host or command assembled from base64 fragmentsSKILL.md:402 · Host or command assembled from base64 fragments-d '{"id":"3","method":"screenshot","params":{}}' | jq -r '.result.data' | base64 -d > /tmp/page.pngFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Host or command assembled from base64 fragmentsSKILL.md:250 · Host or command assembled from base64 fragments-d '{"method":"screenshot"}' | jq -r '.result.data' | base64 -d > /tmp/wifi-settings.pngFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈6,532 tok
1 file · 3 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. Unclaimed publisher≈ +8 on the totalClaim jordancoin: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  4. Host or command assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jordancoinPropose a patch to the maintainer