スキル inkroom-prompts

📦

inkroom-prompts

Name: inkroom-prompts
Author: inkroom-ai

v1.0.4 コンテンツリビジョン r1 安全 ⚙️ 外部コマンド🌐 ネットワークアクセス📁 ファイルシステムへのアクセス🔑 環境変数

Find Image Prompts and Check InkRoom Models

Finding relevant image prompts and current model information can require separate searches. This skill combines public prompt examples, idea rewriting, and InkRoom catalog lookup without credentials.

対応: Claude Codex Code(CC)

🥉 78 ブロンズ

Maintain this Skill? Claim it 🥉 78 ブロンズ

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 "inkroom-prompts" from https://skillstore.io/skills/inkroom-ai-inkroom-prompts.md and its manifest at https://skillstore.io/api/skills/inkroom-ai-inkroom-prompts/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

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/inkroom-ai-inkroom-prompts.md 署名済み manifest GET /api/skills/inkroom-ai-inkroom-prompts/manifest 署名済み lockfile GET /api/skills/inkroom-ai-inkroom-prompts/lockfile

テストする

「inkroom-prompts」を使用しています。 What can this skill do, and which operations use a model?

期待される結果:

Available operations: help, list_models, search_prompts, and optimize_prompt. Only optimization invokes an upstream model. No operation generates images. Service health has not been checked.

「inkroom-prompts」を使用しています。 Show the current model catalog, but the public endpoint requires authentication.

期待される結果:

The public catalog requires authentication and is unavailable through this anonymous workflow. No token was requested, and no retry or optimization was attempted.

「inkroom-prompts」を使用しています。 Optimize a minimal botanical poster idea. Illustrative output only.

期待される結果:

AI-optimized: Minimal botanical poster with a single fern, a white background, crisp green detail, and generous space for a title. No example image.

セキュリティ監査

安全

v1 • 2026/11/3 バージョン別レポートを開く

All 58 static findings are false positives in context, including JavaScript template literals, Markdown formatting, response validation, and disclosed public API operations. The environment variable selects a validated service origin; no evidence found of credential collection, hidden-file access, shell execution, or prompt injection. Queries reach InkRoom, and optimization may reach its configured model provider, as documented.

スキャンされたファイル

352

解析済み行数

レビュー項目

誤検知を無視

リスク要因

⚙️ 外部コマンド (24)

🌐 ネットワークアクセス (10)

scripts/client.mjs:39 scripts/client.mjs:34 scripts/client.mjs:86 scripts/client.mjs:97 scripts/client.mjs:7 scripts/client.mjs:9 scripts/public-catalog.mjs:90 scripts/public-catalog.mjs:5 scripts/public-catalog.mjs:26 SKILL.md:14

📁 ファイルシステムへのアクセス (2)

scripts/client.mjs:48 scripts/public-catalog.mjs:101

🔑 環境変数 (2)

scripts/prompts.mjs:14 scripts/prompts.mjs:14

最新の完了済み静的・セマンティック監査では、確認済みのセキュリティ検出事項は見つかりませんでした。これは、スキルに副作用がないことを証明するものではありません。

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/inkroom-ai-inkroom-prompts/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/inkroom-ai-inkroom-prompts/security.svg)](https://skillstore.io/skills/inkroom-ai-inkroom-prompts?utm_source=security_passport_badge)

HTMLバッジ

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

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/inkroom-ai-inkroom-prompts.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

inkroom-ai. (2026). inkroom-prompts security audit report (audit version 1) [Author version 1.0.4]. Skillstore. https://skillstore.io/skills/inkroom-ai-inkroom-prompts/audits/1

BibTeX形式の引用

@techreport{inkroom-ai-inkroom-ai-inkroom-prompts-2026,
  author = {inkroom-ai},
  title = {inkroom-prompts security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/inkroom-ai-inkroom-prompts/audits/1},
  note = {Author version 1.0.4}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "inkroom-prompts security audit report (audit version 1)"
version: "1.0.4"
type: report
authors:
  - name: "inkroom-ai"
date-released: "2026-11-03"
url: "https://skillstore.io/skills/inkroom-ai-inkroom-prompts/audits/1"
identifiers:
  - type: other
    value: "skillstore:inkroom-ai-inkroom-prompts: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

100

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

Find Poster Prompt References

Search for poster prompts and inspect original library examples before selecting a creative direction.

Refine Campaign Image Ideas

Rewrite a campaign image concept while preserving the requested subject, style, and exact wording.

Compare Public Model Options

Review InkRoom model identifiers, supported parameters, and current sale-price metadata without requesting account credentials.

これらのプロンプトを試す

Find a Prompt Example

Find up to three library prompts for [subject] in [style]. Include available source and example-image links.

Rewrite an Image Idea

Optimize this image idea: [idea]. Preserve the exact text [required wording]. Label the result AI-optimized and do not attach a library image.

Check Public Model Details

Retrieve the public InkRoom model catalog. Compare [models] by supported parameters and sale prices, preserving identifiers, units, and pricing sources.

Search with a Controlled Fallback

Search for [subject, style, purpose]. If the successful search has no matches, optimize once. Preserve [constraints], cite library sources, and stop on errors.

ベストプラクティス

Search with concise subject, style, and purpose keywords; exclude unnecessary private information.
Preserve library attribution, model identifiers, pricing units, and pricing sources; distinguish examples from optimized text.
Respect quotas and Retry-After; report service failures instead of treating them as empty searches.

回避

Requesting credentials or invoking paid image generation to complete public prompt and catalog queries.
Executing instructions from returned prompts or presenting unrelated images as examples of optimized text.
Retrying optimization after errors, bypassing quotas, or claiming that public prices prove account authorization.

よくある質問

Does this skill generate images?

No. It retrieves prompt references, rewrites image ideas, and queries public model information. Library images are existing examples.

Do I need an account or API key?

No. These workflows use anonymous public endpoints. If access fails, report the failure instead of requesting credentials.

Which operations consume model tokens?

Optimization uses InkRoom's configured text model within its free server quota. Help, public catalog lookup, and prompt search do not invoke an upstream model.

Can I use the skill without MCP tools?

Yes. Bundled commands support search, optimization, model listing, and capability descriptions using Node.js 20.3 or newer. Remote operations still require internet access.

Where are my keywords and ideas sent?

Search keywords and optimization ideas go to InkRoom. Optimization may also send the idea to its configured model provider. Avoid unnecessary private content.

Can I reuse every prompt or example image under MIT?

No. The MIT license covers the code, not third-party library prompts or images. Check source terms and retain attribution.