Skills/ClawHub/lgd-skill-review

lgd-skill-review@1.1.20

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 dual-ruler reviewer: reports a structure score (100) and a semantics score (120) as two orthogonal verdicts instead of merging them, and flags the case when the two disagree by 20 points or more. Structure asks whether the package can be used at all (tests, declared-vs-implemented consistency, reproducibility, hygiene, discovery, licensing); semantics asks whether it is worth using (knowledge delta, procedures, anti-patterns with reasons, specification, progressive disclosure, freedom calibration, pattern fit, usability). Every finding carries a stable ID and is traceable to a specific file. Accepts evidence-based appeals: the appellant supplies a path and a check, the engine opens it and rules OVERTURNED / UPHELD, and records the ruling in appeal_log.json. Appeals never silently change a score - they turn a deduction into a verifiable dispute." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher zhaoxinghua09-cell · publishing for 85 daysInstalls 33Last detonated 28 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
3 of 3 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

What changed since 1.1.12

vet-skills diff lgd-skill-review 1.1.12 1.1.20

In the sandbox, this version reached for nothing 1.1.12 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 88/100 (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: handle_appeal.py: error: the following arguments are required: package, appeal
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: review.py: error: the following arguments are required: path
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocess3 of 3 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:305 · 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
File type combined with upload actionSKILL.md:3 · File type combined with upload action — agent may exfiltrate local data files…ine opens it and rules OVERTURNED / UPHELD, and records the ruling in appeal_log.json. Appeals never silently change a score - they turn a deduction into a verifiable dispute.' license: MIT allowed-tools: Read, Glob, Grep, Bash metadata: d…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python exec or eval of computed codescripts/review.py:912 · 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
MEDIUM
Python subprocess execution detectedtests/probe_redteam.py:85 · Python subprocess execution detectedp = subprocess.run([sys.executable, REVIEW, root, "--run"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,743 tok
1 file · 20 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.

lgd-skill-review@1.1.20 safety verdict: Verified (install only) — KillerSkills