lgd-skill-review@1.1.2
VERIFIED· install onlyPublisher 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.
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 deviationsStatic findings
r = 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.for 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.Cost to the agent
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.