📦
routemux-setup
78Connect Your Tools to RouteMux
AI client setup often fails because tools expect different base URL and protocol formats. This skill selects the correct RouteMux endpoint and verifies access.
DevOps＆インフラ 表示
スキル routemux-images
📦
routemux-images
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📁 ファイルシステムへのアクセス🔑 環境変数
Generate and Edit Images with RouteMux
Coding agents can lose built-in image tools when routed through a custom API gateway. This skill uses RouteMux endpoints to generate or edit images.
対応: Claude Codex Code(CC)
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 "routemux-images" from https://skillstore.io/skills/rootfily-ai-routemux-images.md and its manifest at https://skillstore.io/api/skills/rootfily-ai-routemux-images/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。
テストする
「routemux-images」を使用しています。 Create a square app icon showing a white compass on a green field.
期待される結果:
Saved the generated icon to the requested project path. The response used the selected RouteMux image model.
「routemux-images」を使用しています。 Edit the supplied office photo so the wall is light gray while preserving the furniture.
期待される結果:
Saved the edited photo to the requested path and reported the model that completed the edit.
「routemux-images」を使用しています。 Generate a wide editorial illustration and verify its dimensions.
期待される結果:
- Saved one generated illustration to the requested path.
- Reported the requested aspect ratio, actual file dimensions, and responding model.
セキュリティ監査
高リスクv1 • 2026/9/15 バージョン別レポートを開く
The skill intentionally uses curl, RouteMux network endpoints, a dedicated API key, and user-selected files. Most backtick alerts are Markdown false positives, but unsafe shell interpolation and plaintext shell-profile storage create credible risks.
1
スキャンされたファイル
103
解析済み行数
9
レビュー項目
0
誤検知を無視
確認済みのセキュリティ上の懸念 (2)
高
Shell Injection Through Prompt and Path Placeholders
User-derived prompt and path placeholders appear directly in shell command templates without structured argument handling.
The prompt is placed inside shell quotes and the image path is unquoted, allowing metacharacters to alter command interpretation.
中
Unvalidated Response URL Download
The workflow instructs the agent to download any URL returned by the service without scheme, host, size, or content validation.
The download instruction is explicit, while safeguards for service-controlled URLs are absent.
機能レビュー項目 (9)
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
Hidden file in home directory
Add that line to ~/.zshrc (or ~/.bashrc) so new terminals have it too.
The instructions recommend persisting the plaintext API key in a shell profile under the user's home directory.
高
Hidden file access
Add that line to ~/.zshrc (or ~/.bashrc) so new terminals have it too.
The setup guidance directs users to modify hidden shell configuration files with a persistent plaintext secret.
中
Ruby/shell backtick execution
```bash
The fenced block invokes curl and sends an authorization header to RouteMux to retrieve the model catalogue.
中
Ruby/shell backtick execution
```bash
The fenced block instructs the agent to execute a local image-generation shell script with user-derived arguments.
中
Ruby/shell backtick execution
```bash
The fenced block invokes curl to submit image prompts and credentials to the RouteMux generation endpoint.
中
Ruby/shell backtick execution
```bash
The fenced block invokes curl to upload an image and API credential to the RouteMux editing endpoint.
低
Hardcoded URL
curl -s "https://api.routemux.com/v1/models?capability=image_generation" \
The skill intentionally queries the RouteMux API and transmits its API credential over the network.
低
Hardcoded URL
curl -s https://api.routemux.com/v1/images/generations \
The skill intentionally sends the user's prompt and API credential to the RouteMux generation endpoint.
低
Hardcoded URL
curl -s https://api.routemux.com/v1/images/edits \
The skill intentionally uploads an input image, edit prompt, and API credential to RouteMux.
リスク要因
⚙️ 外部コマンド (26)
SKILL.md:11 SKILL.md:12 SKILL.md:19 SKILL.md:22-28 SKILL.md:28-33 SKILL.md:33-36 SKILL.md:36-39 SKILL.md:39-43 SKILL.md:43-45 SKILL.md:45-47 SKILL.md:47-52 SKILL.md:52-53 SKILL.md:53-54 SKILL.md:54-62 SKILL.md:62-64 SKILL.md:64-70 SKILL.md:70-74 SKILL.md:74-83 SKILL.md:83-84 SKILL.md:84-85 SKILL.md:85-86 SKILL.md:86-87 SKILL.md:87-88 SKILL.md:88-90 SKILL.md:90-94 SKILL.md:94-97
🌐 ネットワークアクセス (5)
📁 ファイルシステムへのアクセス (2)
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。
レポートリンクをコピー
https://skillstore.io/skills/rootfily-ai-routemux-images/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/rootfily-ai-routemux-images?utm_source=security_passport_badge)HTMLバッジ
<a href="https://skillstore.io/skills/rootfily-ai-routemux-images?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/rootfily-ai-routemux-images/security.svg" alt="Skillstore security assessment" loading="lazy"></a>埋め込みカード
<iframe src="https://skillstore.io/embed/skills/rootfily-ai-routemux-images.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
rootfily-ai. (2026). routemux-images security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/rootfily-ai-routemux-images/audits/1BibTeX形式の引用
@techreport{rootfily-ai-rootfily-ai-routemux-images-2026,
author = {rootfily-ai},
title = {routemux-images security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/rootfily-ai-routemux-images/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: "routemux-images security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "rootfily-ai"
date-released: "2026-09-15"
url: "https://skillstore.io/skills/rootfily-ai-routemux-images/audits/1"
identifiers:
- type: other
value: "skillstore:rootfily-ai-routemux-images: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 55
アーキテクチャ
85
保守性
85
コンテンツ
65
コミュニティ
91
仕様準拠
作成できるもの
Create Product Visuals
Generate a focused product mockup and save it inside the active project.
Produce Application Assets
Create icons, illustrations, or backgrounds when built-in image tools are unavailable.
Revise Existing Artwork
Upload an image and request a targeted visual change through RouteMux.
これらのプロンプトを試す
Generate a Simple Image
Generate an image of [subject] in [style]. Save it as [output path].
Set Composition and Ratio
Create [subject] with [composition], [lighting], and [color palette]. Use a [aspect ratio] format and save it to [output path].
Edit an Existing Image
Edit [input image path] to [requested change]. Preserve [elements to keep] and save the result as [output path].
Choose and Verify a Model
Query current RouteMux image models, select one suitable for [requirements], create [image brief], verify the returned dimensions, and report the responding model.
ベストプラクティス
- Provide a precise subject, composition, style, and aspect ratio.
- Choose an output path inside the active working directory.
- Review the reported model and actual dimensions before using the asset.
回避
- Do not place real API keys in prompts, files, logs, or replies.
- Do not request many variants in one call to reduce network usage.
- Do not assume a model slug or exact pixel size remains stable.
よくある質問
What credential does this skill require?
It requires ROUTEMUX_API_KEY in the environment and should not search other credential stores.
Can it edit an existing image?
Yes. It uploads one input image with a text instruction to the RouteMux editing endpoint.
How does it choose an image model?
It queries the live RouteMux catalogue and selects a model that supports image generation.
Can it guarantee exact dimensions?
No. The requested size reliably guides aspect ratio, but upstream models may return different pixel dimensions.
Where does it save generated images?
It saves each image to the user-selected artifact path, normally inside the active working directory.
What happens when RouteMux returns an error?
It interprets documented errors, limits retries for temporary failures, and reports the request identifier when available.
開発者情報
作成者
rootfily-aiライセンス
MIT
Skillstore リビジョン
r1
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。
参照
f6aa6f4e154bf3a8f90ac2069cbe691b8c5a5980
メンテナンスの新しさ
2026/9/15
利用状況
0 ダウンロード · 0 閲覧
ファイル構成
📄 SKILL.md
rootfily-ai のその他のスキル
すべて表示📦
routemux-models
78Check RouteMux Models and Capabilities
Choosing a model without current availability, pricing, or capability data can cause failed requests and poor tradeoffs. This skill queries the live RouteMux catalogue for the models your key can call.
調査＆学習 表示
📦
routemux-video
38Generate Videos with RouteMux
Video generation APIs require model selection, asynchronous polling, and careful download handling. This skill guides RouteMux submissions and returns completed video files with status details.
デザイン＆クリエイティブ 表示
関連スキル
すべて表示📦
imagegen
82Create and Edit Project Images
作成者 openai
Producing consistent raster assets requires precise prompts, careful edits, and reliable output handling. This skill structures requests, creates or edits visuals, validates results, and saves project-ready files.
デザイン＆クリエイティブ 表示
📦
gpt-image-2
78RunComfyでGPT Image 2アセットを生成
作成者 runcomfy-com
チームには、テキスト、レイアウト、ブランドの詳細を維持する画像プロンプトと編集が必要です。このスキルは、Claude、Codex、Claude CodeがRunComfyのGPT Image 2エンドポイントを、明確なサイズ、編集、プライバシールールに従って使用できるようにガイドします。
デザイン＆クリエイティブ 表示
📦
nano-banana-2
78inference.shでGemini画像を生成
作成者 inferen-sh
画像作成では、モデルコマンドやオプションの詳細が必要になることがよくあります。このスキルは、inference.shを通じたGemini画像生成向けに、すぐ使えるプロンプトとCLIパターンを提供します。
デザイン＆クリエイティブ 表示
📦
native-transparent-imagegen
86Generate Native-Alpha Transparent Images
作成者 zseven-w
Image generators can return opaque files or painted checkerboards when transparency is required. This skill generates native-alpha assets and validates every untouched output.
デザイン＆クリエイティブ 表示
📦
generating-storyboards
82Create Consistent Video Storyboards
作成者 supercmohq
Video concepts can lose continuity when clips are planned separately. This skill creates sequential storyboard sheets that preserve characters, products, settings, and visual states.
デザイン＆クリエイティブ 表示
📦
generating-ai-actors
82Create Reusable Photorealistic AI Actors
作成者 supercmohq
Campaign teams need consistent fictional talent without supplying a person photograph. This skill creates one detailed adult identity that can guide later image and video generation.
デザイン＆クリエイティブ 表示