clawtk@1.1.0

VERIFIED· install only

Publisher claims: "Automatically reduce OpenClaw API costs by 60-80%. One-command setup: config optimization, spend caps, retry loop protection, and ClawTK Engine compression." Observed in sandbox: calls raw.githubusercontent.com only, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher skl3 · publishing for 233 daysInstalls 991Last detonated 36 min ago
$clawhub install clawtk
WatchReport an issue

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 · 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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 82/100 (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: calls raw.githubusercontent.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexec /usr/bin/dirname
0.0sprocessexec /usr/bin/tail
0.0sprocessexited 1: [clawtk] Install it: brew install jq (macOS) or apt install jq (Linux)
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1: [clawtk] Purchase a key at https://clawtk.co/pro
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2snetworkCONNECT tcp://raw.githubusercontent.com:443 · not in the allow-list, refused
0.2sprocessexec /usr/bin/dirname
0.2sprocessexec /usr/bin/uname
0.2sprocessexec /usr/bin/cat
0.2sprocessexec /usr/bin/tr
0.2sprocessexec /usr/bin/mktemp
0.2sprocessexec /usr/bin/curl
0.2sprocessexec /usr/bin/wc
0.2sprocessexec /usr/bin/rm
0.2sprocessexited 1: [clawtk] Binary: https://github.com/rtk-ai/rtk/releases
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: [clawtk] Install it: brew install jq (macOS) or apt install jq (Linux)
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: [clawtk] ClawTK is not set up. Run /clawtk setup first.
0.2sprocessbundled script run in the sandbox with no arguments
0.3sfilesystemread ~/.openclaw/ outside project
0.3sprocessexec /usr/bin/rm
0.3sprocess6 of 6 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /usr/bin/tail
0.3sprocessexited 1: [clawtk] Install it: brew install jq (macOS) or apt install jq (Linux)

Static findings

HIGH
Direct script execution from GitHub raw URLscripts/install-engine.sh:99 · Direct script execution from GitHub raw URL — unverified code sourcelocal installer_url="https://raw.githubusercontent.com/rtk-ai/rtk/refs/tags/v${rtk_version}/install.sh"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 2,145 lines in 18 files.

Cost to the agent

Instructions loaded
≈1,131 tok
1 file · 18 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.

clawtk@1.1.0 safety verdict: Verified (install only) — KillerSkills