Skills/ClawHub/lgd-skill-review

lgd-skill-review@1.1.2

VERIFIED· install only

Publisher claims: "Use when reviewing, auditing or scoring any AI skill package, or when a skill was rejected and you need to know why. A six-dimension, evidence-based reviewer: it scores structure, declared-vs-implemented consistency, reproducibility, hygiene/sanitization, AI discoverability and licensing on a weighted 100-point scale, then emits a prioritized fix list (P0 blocking / P1 improvement) and a rerun command. Designed to close the loop: review -> fix -> re-review, so an agent can improve its own skill autonomously. Every point is traceable to a specific file and finding; no impression scoring. Detects the industry's most common defect: documentation promising a command or flag that the script never implements. Zero dependency, standard library only, offline. Triggers: review my skill, audit skill quality, why is my skill rejected, skill checklist, score this skill, improve my SKILL.md, skill package gate." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher zhaoxinghua09-cell · publishing for 85 daysInstalls 33Last detonated 31 min ago
$clawhub install lgd-skill-review
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 90/100 (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
0.1sprocessexited 2: review.py: error: the following arguments are required: path
0.1sprocessbundled script run in the sandbox with no arguments
0.3sprocess2 of 2 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/review.py:200 · Python subprocess execution detectedr = subprocess.run([sys.executable, runner], cwd=root, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python exec or eval of computed codescripts/review.py:575 · Python exec or eval of computed codefor pat in ["eval(", "exec(", "os.system", "pickle.loads"]:Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05

Cost to the agent

Instructions loaded
≈1,711 tok
1 file · 14 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.