スキル alan-test-feature
📦
alan-test-feature
v1.1.1 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
Test Features and Publish Evidence Reports
Manual feature testing can miss edge cases and leave evidence scattered. This skill plans browser scenarios, captures results, uploads media, and creates a structured Alan report.
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 "alan-test-feature" from https://skillstore.io/skills/supatest-ai-alan-test-feature.md and its manifest at https://skillstore.io/api/skills/supatest-ai-alan-test-feature/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
「alan-test-feature」を使用しています。 Test the new account settings form with standard coverage.
期待される結果:
A mixed-status report covers saving valid changes, required-field validation, duplicate submission, and server failure. Two reproducible issues include screenshot evidence.
「alan-test-feature」を使用しています。 Run a light check of the updated checkout confirmation page.
期待される結果:
A passing report documents navigation, purchase confirmation, persisted order details, and final visual evidence.
「alan-test-feature」を使用しています。 Test the dashboard comprehensively on desktop and mobile widths.
期待される結果:
A comprehensive report summarizes responsive layouts, empty states, authorization behavior, navigation, and recoverable API failures with linked media.
セキュリティ監査
高リスクv1 • 2026/8/20 バージョン別レポートを開く
Most backtick, localhost, device-file, and reconnaissance alerts are false positives caused by Markdown examples or bounded local testing. Confirmed risks include unpinned global installation, repository script execution, environment-file access, predictable temporary storage, and mandatory capture uploads. Media can contain credentials or private application data and is uploaded without a review gate.
1
スキャンされたファイル
440
解析済み行数
16
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 (13)
高
Environment file access
4. Check for `Procfile`, `.env`, `Pipfile`, `requirements.txt`, `Gemfile`
The discovery step includes checking .env while determining how to run the project. It may expose unrelated credentials even though the exact read method is not specified.
高
Environment file access
- Check `.env` or `.env.local` for `PORT` or `VITE_PORT` or similar
The skill explicitly directs the agent to inspect .env and .env.local. These files commonly contain credentials beyond the requested port value.
高
Environment variant files
- Check `.env` or `.env.local` for `PORT` or `VITE_PORT` or similar
The skill explicitly directs the agent to inspect .env and .env.local. These files commonly contain credentials beyond the requested port value.
高
Screen capture upload
description: Scope coverage, build a testing strategy, test the feature with agent-browser, capture
The workflow requires captured application screens to be uploaded and referenced from a persistent report. Sensitive UI data can leave the local environment without a review gate.
高
Screen capture upload
Analyze the current branch's changes, scope the coverage level with the user, build an explicit test
The workflow requires captured application screens to be uploaded and referenced from a persistent report. Sensitive UI data can leave the local environment without a review gate.
高
Screen capture upload
All captures (screenshots, videos) MUST be written to `/tmp/alan-captures/`.
This mandatory capture is part of the workflow that uploads every screenshot and video to S3. The image may contain credentials, personal data, or private application state.
高
Screen capture upload
> - If you are tempted to create a `reports/` or `screenshots/` folder anywhere other than `/tmp/`,
This mandatory capture is part of the workflow that uploads every screenshot and video to S3. The image may contain credentials, personal data, or private application state.
高
Screen capture upload
agent-browser --session test-feature screenshot /tmp/alan-captures/step-00-initial-state.png
This mandatory capture is part of the workflow that uploads every screenshot and video to S3. The image may contain credentials, personal data, or private application state.
確認済みの13件をすべて表示
高
Screen capture upload
agent-browser --session test-feature screenshot /tmp/alan-captures/step-NN-description.png
This mandatory capture is part of the workflow that uploads every screenshot and video to S3. The image may contain credentials, personal data, or private application state.
高
Screen capture upload
agent-browser --session test-feature screenshot /tmp/alan-captures/final-state.png
This mandatory capture is part of the workflow that uploads every screenshot and video to S3. The image may contain credentials, personal data, or private application state.
高
Screen capture upload
"screenshotUrl": "<s3Key from Phase 3 — e.g. sandbox-captures/org/task/step-01.png — omit if upload
The workflow requires captured application screens to be uploaded and referenced from a persistent report. Sensitive UI data can leave the local environment without a review gate.
高
Screen capture upload
"screenshotUrl": "<s3Key from Phase 3 showing the issue — omit if upload failed>"
The workflow requires captured application screens to be uploaded and referenced from a persistent report. Sensitive UI data can leave the local environment without a review gate.
高
Screen capture upload
- **screenshotUrls**: flat list of ALL screenshot s3Keys from Phase 3 (for gallery display). Use the
The workflow requires captured application screens to be uploaded and referenced from a persistent report. Sensitive UI data can leave the local environment without a review gate.
機能レビュー項目 (16)
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
Ruby/shell backtick execution
Analyze the current branch's changes, scope the coverage level with the user, build an explicit test
The instruction starts project processes and mandates uploading browser captures to S3. These are consequential external actions that can execute repository code and disclose application data.
高
Ruby/shell backtick execution
```bash
The fenced command installs an unpinned npm package globally and runs its installer. A compromised or changed package could execute arbitrary code with the agent's permissions.
高
Ruby/shell backtick execution
```bash
The command block starts repository-defined npm, Python, Ruby, or Docker services. Those startup paths can execute untrusted project code and alter the local environment.
高
Ruby/shell backtick execution
For each captured file, use the `mcp__alan__get_upload_url` MCP tool to get a presigned S3 URL, then
This instruction explicitly sends every captured file to S3 through a presigned URL. Captures can contain credentials, personal data, or unreleased application details.
高
Ruby/shell backtick execution
```bash
The fenced curl command performs the external PUT that uploads a local screenshot. This is a direct data-transfer action with no content review or approval gate.
中
Temp directory access
All captures (screenshots, videos) MUST be written to `/tmp/alan-captures/`.
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
mkdir -p /tmp/alan-captures
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
> - **ONLY** write capture files to `/tmp/alan-captures/`. Never anywhere else.
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
> - If you are tempted to create a `reports/` or `screenshots/` folder anywhere other than `/tmp/`,
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
agent-browser --session test-feature record start /tmp/alan-captures/happy-path.webm
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
agent-browser --session test-feature screenshot /tmp/alan-captures/step-00-initial-state.png
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
agent-browser --session test-feature screenshot /tmp/alan-captures/step-NN-description.png
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
agent-browser --session test-feature screenshot /tmp/alan-captures/final-state.png
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
for f in /tmp/alan-captures/*.webm; do
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
SIZE=$(stat -c%s "/tmp/alan-captures/step-01.png" 2>/dev/null || stat -f%z "/tmp/alan-captures/step-
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
中
Temp directory access
--data-binary @/tmp/alan-captures/step-01.png
The skill mandates predictable names under a shared /tmp directory without restrictive permissions or symlink checks. Captures may be exposed or redirected on multi-user systems.
リスク要因
⚙️ 外部コマンド (50)
SKILL.md:9 SKILL.md:19 SKILL.md:20 SKILL.md:21 SKILL.md:23 SKILL.md:27 SKILL.md:29-31 SKILL.md:31-34 SKILL.md:34-36 SKILL.md:36-39 SKILL.md:39-41 SKILL.md:41-45 SKILL.md:45-47 SKILL.md:47-49 SKILL.md:49-52 SKILL.md:52-53 SKILL.md:53 SKILL.md:54-55 SKILL.md:55 SKILL.md:65-67 SKILL.md:67-75 SKILL.md:75-81 SKILL.md:81 SKILL.md:109-112 SKILL.md:112-123 SKILL.md:123 SKILL.md:124 SKILL.md:125 SKILL.md:126 SKILL.md:127 SKILL.md:130-144 SKILL.md:144-149 SKILL.md:149-155 SKILL.md:155-162 SKILL.md:162 SKILL.md:163-164 SKILL.md:164-210 SKILL.md:210-220 SKILL.md:220-222 SKILL.md:222 SKILL.md:226-229 SKILL.md:229-235 SKILL.md:235-237 SKILL.md:237-245 SKILL.md:245-247 SKILL.md:247-254 SKILL.md:254-255 SKILL.md:255 SKILL.md:256 SKILL.md:258-260
🌐 ネットワークアクセス (5)
検出されたパターン
Screen capture upload×10
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/supatest-ai-alan-test-feature/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/supatest-ai-alan-test-feature?utm_source=security_passport_badge)HTMLバッジ
<a href="https://skillstore.io/skills/supatest-ai-alan-test-feature?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/supatest-ai-alan-test-feature/security.svg" alt="Skillstore security assessment" loading="lazy"></a>埋め込みカード
<iframe src="https://skillstore.io/embed/skills/supatest-ai-alan-test-feature.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
supatest-ai. (2026). alan-test-feature security audit report (audit version 1) [Author version 1.1.1]. Skillstore. https://skillstore.io/skills/supatest-ai-alan-test-feature/audits/1BibTeX形式の引用
@techreport{supatest-ai-supatest-ai-alan-test-feature-2026,
author = {supatest-ai},
title = {alan-test-feature security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/supatest-ai-alan-test-feature/audits/1},
note = {Author version 1.1.1}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "alan-test-feature security audit report (audit version 1)"
version: "1.1.1"
type: report
authors:
- name: "supatest-ai"
date-released: "2026-08-20"
url: "https://skillstore.io/skills/supatest-ai-alan-test-feature/audits/1"
identifiers:
- type: other
value: "skillstore:supatest-ai-alan-test-feature: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
100
保守性
87
コンテンツ
65
コミュニティ
91
仕様準拠
作成できるもの
Validate a Pull Request
Test changed user flows before review and attach visual evidence to a structured report.
Verify Acceptance Criteria
Run agreed scenarios and document passes, failures, and reproducible defects for a feature.
Review a Release Candidate
Check critical workflows, edge cases, responsiveness, and navigation before a release decision.
これらのプロンプトを試す
Run a Light Feature Check
Test the current feature with light coverage. Confirm the main path, capture required evidence, and create the Alan test report.
Run Standard Feature Testing
Test [feature] with standard coverage. Include the happy path, validation failures, key error states, and a structured report.
Run Comprehensive Browser Testing
Test [feature] comprehensively. Cover boundaries, permissions, responsiveness, navigation, and recoverable failures. Record separate videos when needed.
Design Risk-Based Change Coverage
Analyze changes between [base branch] and HEAD. Design risk-based scenarios for [feature], execute them, and report reproducible defects with evidence.
ベストプラクティス
- Provide acceptance criteria, test accounts, and known risks before execution.
- Review captures for secrets and personal data before approving uploads.
- Use stable test data and isolate tests from production systems.
回避
- Do not provide production credentials or unrestricted administrative accounts.
- Do not upload captures before checking visible data and browser state.
- Do not treat browser testing as complete security or regression coverage.
よくある質問
What coverage levels are supported?
Light covers the main path. Standard adds key edge cases and errors. Comprehensive adds boundaries, responsiveness, navigation, and broader failure states.
Does the skill start the application?
Yes. It inspects common project files, selects a likely development command, starts the server, and checks its local port.
Which browser tool does it use?
It uses the agent-browser command-line tool for navigation, interaction, screenshots, and recording.
Are screenshots and videos required?
The current workflow requires screenshots and attempts video recording. Users should review media before any external upload.
Where is the final report created?
The skill calls the Alan report tool to create a structured artifact linked to the active task, conversation, and team.
Can it test production systems?
The workflow targets a local development server. Production testing requires separate authorization, data controls, and operational safeguards.
開発者情報
作成者
supatest-aiライセンス
MIT
作者バージョン
v1.1.1
Skillstore リビジョン
r1
参照
bdb71a4bc34515f37772ae85fd5501f9c2ff33b0
メンテナンスの新しさ
2026/8/20
利用状況
0 ダウンロード · 1 閲覧
ファイル構成
📄 SKILL.md