Skills/ClawHub/openclaw-self-improve

openclaw-self-improve@1.3.0

VERIFIED· install only

Publisher claims: "Evidence-based, approval-gated self-improvement workflow for OpenClaw. Use when the user asks to make OpenClaw or any project more reliable, faster, cheaper,..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher gopendrasharma89-tech · publishing for 193 daysInstalls 1,628Last detonated 22 min ago
$clawhub install openclaw-self-improve
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 10 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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 2026-11-22 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: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /usr/bin/cat
0.0sprocessexited 1: Prints the absolute path of the created backup file on success.
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/cat
0.1sprocessexited 2: 2 bad arguments / run dir missing / required artifacts missing
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/cat
0.1sprocessexited 1: -h, --help Show this message
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: export-improvement-run-json.py: error: the following arguments are required: --run-dir
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexec /usr/bin/cat
0.2sprocessexited 1: run-info.md baseline.md hypotheses.md proposal.md validation.md outcome.md
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexec /usr/bin/cat
0.3sprocessexited 1: 3 no matching runs found (useful for scripts)
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessexec /usr/bin/cat
0.3sprocessexited 1: rejected | blocked
0.3sprocess8 of 10 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

HIGH
Destructive file system command detectedscripts/init-improvement-run.sh:240 · Destructive file system command detectedrm -f \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicescripts/init-improvement-run.sh:240 · Destructive command against a filesystem root or devicerm -f \Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,987 tok
1 file · 16 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.