📦

lavish

Name: lavish
Author: kunchenguid

コンテンツリビジョン r1 高リスク ⚙️ 外部コマンド🌐 ネットワークアクセス

Create Interactive HTML Review Artifacts

Complex responses are difficult to review in plain text. Lavish creates interactive HTML artifacts that collect visual annotations and structured feedback.

対応: Claude Codex Code(CC)

⚠️ 38 不十分

インストール前に停止して確認を求めてください。

計画を確認し、ファイルを変更する前にユーザーの明示的な同意を得てください。

自分のエージェントでインストール

このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。

エージェントリクエスト

Review the Skillstore skill "lavish" from https://skillstore.io/skills/kunchenguid-lavish.md and its manifest at https://skillstore.io/api/skills/kunchenguid-lavish/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。

エージェントが読めるリソース

AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。

Markdown詳細 GET /skills/kunchenguid-lavish.md 署名済み manifest GET /api/skills/kunchenguid-lavish/manifest 署名済み lockfile GET /api/skills/kunchenguid-lavish/lockfile

テストする

「lavish」を使用しています。 Compare three database options for an analytics service.

期待される結果:

A browser artifact presents a decision matrix, operational tradeoffs, cost factors, risks, and annotated recommendation areas.

「lavish」を使用しています。 Explain the proposed authentication architecture.

期待される結果:

An interactive architecture review shows the request flow, trust boundaries, component duties, failure modes, and questions for reviewers.

「lavish」を使用しています。 Review the checkout redesign plan.

期待される結果:

A structured plan displays milestones, interface states, dependencies, risks, and focused controls for stakeholder feedback.

セキュリティ監査

高リスク

v1 • 2026/8/23 バージョン別レポートを開く

Most static findings are false positives caused by Markdown code spans. Confirmed risks include unpinned npx execution and public third-party sharing without an explicit consent gate. No prompt injection or malicious reconnaissance was found.

スキャンされたファイル

解析済み行数

レビュー項目

誤検知を無視

確認済みのセキュリティ上の懸念 (2)

高

SKILL.md:83

Public Third-Party Publishing Without Consent Gate

The share command publishes artifacts to ht-ml.app publicly by default, but the workflow does not require explicit user consent or a sensitive-data check.

Line 83 explicitly states that sharing uses a third-party service and that links are public by default.

中

SKILL.md:83

Secrets Exposed Through Command-Line Arguments

The share command accepts passwords and bearer tokens as arguments, which may expose secrets through shell history or process listings.

Line 83 directly documents password and token flags; command-line secrets commonly remain visible to local process and history mechanisms.

機能レビュー項目 (18)

これらは、このスキルに期待される可能性のある実際のローカル機能であるため、レビューが必要ですが、確認済みの悪意ある動作としてはカウントされません。

高

SKILL.md:83

Ruby/shell backtick execution

- Run `npx -y lavish-axi share <html-file> [--password <pw>] [--token <t>]` to publish the artifact

The command executes package code and can upload an artifact to a public third-party service.

中

SKILL.md:14

Ruby/shell backtick execution

Lavish Editor helps agents turn rich HTML artifacts into collaborative human review surfaces. Whenev

The workflow explicitly runs unpinned lavish-axi code through npx, creating package supply-chain and arbitrary code execution exposure.

中

SKILL.md:16

Ruby/shell backtick execution

You do not need lavish-axi installed globally - invoke it with `npx -y lavish-axi <html-file>`.

This line explicitly directs unattended npx download and execution of lavish-axi without a pinned version.

中

SKILL.md:17

Ruby/shell backtick execution

If lavish-axi output shows a follow-up command starting with `lavish-axi`, run it as `npx -y lavish-

The agent is directed to transform CLI output into another npx command, extending trust to package-generated instructions.

中

SKILL.md:34

Ruby/shell backtick execution

2. Run `npx -y lavish-axi <html-file>` to open or resume a review session in the browser.

This instruction executes unpinned lavish-axi package code through npx.

中

SKILL.md:36

Ruby/shell backtick execution

3. Run `npx -y lavish-axi poll <html-file>` to long-poll for the user's annotations and queued promp

The line directs execution of the unpinned package and starts a long-running poll process.

中

SKILL.md:49

Ruby/shell backtick execution

6. Run `npx -y lavish-axi end <html-file>` when the review is finished.

This line explicitly executes the unpinned lavish-axi package through npx to end a session.

中

SKILL.md:62

Ruby/shell backtick execution

Run `npx -y lavish-axi playbook <id>` for focused, detailed guidance on any of these.

This instruction runs an unpinned package command to retrieve playbook guidance.

中

SKILL.md:64

Ruby/shell backtick execution

For flows, architecture, state, or sequence diagrams, do not hand-build boxes-and-arrows from div/fl

The line explicitly invokes the unpinned package design command before generating diagrams.

中

SKILL.md:76

Ruby/shell backtick execution

- Run `npx -y lavish-axi <html-file>` to open or resume a Lavish Editor session. If the user explici

This line instructs the agent to execute unpinned lavish-axi code through npx.

中

SKILL.md:79

Ruby/shell backtick execution

- Run `npx -y lavish-axi poll <html-file>` to wait for user feedback. It long-polls and stays silent

The line executes an unpinned package command and starts a persistent polling process.

中

SKILL.md:81

Ruby/shell backtick execution

- Run `npx -y lavish-axi end <html-file>` to end a session as the agent - ending it this way still a

This instruction executes the unpinned package through npx to end a session.

中

SKILL.md:82

Ruby/shell backtick execution

- Run `npx -y lavish-axi export <html-file> [--out <path>]` to write a portable copy of the artifact

This instruction executes package code and writes an exported artifact to a supplied filesystem path.

中

SKILL.md:84

Ruby/shell backtick execution

- Run `npx -y lavish-axi stop` to shut down the background server (it also self-stops when idle or a

This line executes the unpinned package through npx to stop its background server.

中

SKILL.md:85

Ruby/shell backtick execution

- Run `npx -y lavish-axi playbook <playbook_id>` for focused artifact guidance. One artifact often c

This line executes an unpinned package command to retrieve playbook guidance.

中

SKILL.md:86

Ruby/shell backtick execution

- Lavish does not auto-inject any design system - artifacts stay portable so they render identically

The instruction executes the unpinned design command and may provide remote CDN references for generated artifacts.

中

SKILL.md:18

Shell command substitution

In restricted subprocess sandboxes, CI, or agent harnesses where `npx -y` exits opaquely (for exampl

Both fallback commands use shell substitution to resolve npm paths before executing package code.

低

SKILL.md:83

Hardcoded URL

- Run `npx -y lavish-axi share <html-file> [--password <pw>] [--token <t>]` to publish the artifact

The skill explicitly targets ht-ml.app for artifact uploads, and the service is third-party and public by default.

リスク要因

⚙️ 外部コマンド (38)

🌐 ネットワークアクセス (1)

SKILL.md:83

監査者: codex

このレポートを共有・引用

バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。

バージョン別レポートを開く

レポートリンクをコピー

https://skillstore.io/skills/kunchenguid-lavish/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

[![Skillstore security assessment](https://skillstore.io/badges/skills/kunchenguid-lavish/security.svg)](https://skillstore.io/skills/kunchenguid-lavish?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/kunchenguid-lavish?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/kunchenguid-lavish/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/kunchenguid-lavish.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学術引用 (APA · BibTeX · CFF)

APA形式の引用

kunchenguid. (2026). lavish security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/kunchenguid-lavish/audits/1

BibTeX形式の引用

@techreport{kunchenguid-kunchenguid-lavish-2026,
  author = {kunchenguid},
  title = {lavish security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/kunchenguid-lavish/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "lavish security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "kunchenguid"
date-released: "2026-08-23"
url: "https://skillstore.io/skills/kunchenguid-lavish/audits/1"
identifiers:
  - type: other
    value: "skillstore:kunchenguid-lavish:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore スコア

このスコアの理由証拠の信頼度: 中

アーキテクチャ

保守性

コンテンツ

コミュニティ

仕様準拠

作成できるもの

Review Technical Plans

Present architecture, dependencies, risks, and decisions in an annotated browser artifact.

Compare Product Options

Organize alternatives, tradeoffs, and open questions for focused stakeholder feedback.

Inspect Code Changes

Show diffs, annotated snippets, and before-and-after behavior in a visual review surface.

これらのプロンプトを試す

Create a Simple Comparison

Create a Lavish comparison artifact for [options]. Show key differences, benefits, risks, and a clear recommendation.

Visualize a Technical Plan

Build a Lavish plan for [project]. Include scope, milestones, dependencies, risks, decisions, and questions requiring feedback.

Review an Architecture

Create a Lavish architecture artifact for [system]. Add a Mermaid diagram, component responsibilities, data flows, failure modes, and decision points.

Build a Multi-Surface Review

Build a Lavish review combining plan, comparison, diagram, and input playbooks for [initiative]. Collect prioritized decisions and actionable annotations.

ベストプラクティス

Match the artifact design to the subject project and the user's requested visual style.
Keep polling in a tracked foreground process and apply only feedback the user submits.
Confirm user intent and remove sensitive information before any external share.

回避

Do not publish artifacts to third-party hosting without explicit user approval.
Do not detach polling with untracked shell background processes.
Do not replace requested visual structure with long, unformatted prose.

よくある質問

What does Lavish create?

It creates interactive HTML artifacts for visual explanation, review, annotation, and feedback.

Which AI tools are supported?

The report declares support for Claude, Codex, and Claude Code.

Does Lavish require a global installation?

No. The documented workflow uses npx, but Node.js and package access are required.

Can reviewers edit diagrams?

Yes. Supported Mermaid diagrams can open as editable Excalidraw whiteboards during a review session.

Can artifacts work without the local server?

Yes. Exported artifacts inline local assets, but remote references still require network access.

Is external sharing private?

No. Shares are public by default unless password protection is selected, and content is uploaded to a third-party service.

開発者情報

作成者

kunchenguid

ライセンス

MIT

Skillstore リビジョン

バージョンに関する注意

作者はバージョンを宣言していません。

リポジトリ

https://github.com/kunchenguid/lavish-axi/tree/8a0e25402a1d461d37b95c92c6c5f3ce8f143fc4/skills/lavish

参照

6887c2ead4c74300240c16e1d85ef6f6c827a820

メンテナンスの新しさ

2026/8/23

利用状況

1 ダウンロード · 0 閲覧

ファイル構成

📄 SKILL.md