スキル xcrawl-scrape

📦

xcrawl-scrape

Name: xcrawl-scrape
Author: xcrawl-api

v1.0.2 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

Extract Web Page Data with XCrawl

Web pages contain content that is difficult to collect in consistent formats. This skill guides XCrawl requests for page content, structured extraction, and asynchronous result retrieval.

対応: Claude Codex Code(CC)

⚠️ 38 不十分

Maintain this Skill? Claim it ⚠️ 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 "xcrawl-scrape" from https://skillstore.io/skills/xcrawl-api-xcrawl-scrape.md and its manifest at https://skillstore.io/api/skills/xcrawl-api-xcrawl-scrape/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/xcrawl-api-xcrawl-scrape.md 署名済み manifest GET /api/skills/xcrawl-api-xcrawl-scrape/manifest 署名済み lockfile GET /api/skills/xcrawl-api-xcrawl-scrape/lockfile

テストする

「xcrawl-scrape」を使用しています。 Illustrative request: fetch a public article as Markdown and links, then summarize the result.

期待される結果:

Illustrative summary: the synchronous scrape completed with Markdown and links.
The response includes the page title, extracted content, outgoing links, and task metadata.
Actual content and credit usage depend on the upstream response.

「xcrawl-scrape」を使用しています。 Illustrative request: extract product title, price, and currency asynchronously, then summarize task status.

期待される結果:

Illustrative summary: the task progressed from pending to completed.
The extracted title is Sample Product, the price is 49, and the currency is USD.
These values are examples, not results from a live scrape.

セキュリティ監査

高リスク

v1 • 2026/10/17 バージョン別レポートを開く

All 150 static findings describe Markdown syntax, intended API calls, or dedicated configuration access rather than the alleged threats. Two contextual risks remain: disabled target TLS verification by default and unredacted request payloads that can expose supplied credentials. No evidence found of malicious intent, unauthorized credential collection, or embedded prompt injection.

スキャンされたファイル

255

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:127-128 SKILL.md:165-166 SKILL.md:239-246

Output Contract Can Disclose Supplied Credentials

The output contract requires returning the request_payload used for the request without any redaction instruction. Supported payload fields include cookies, request headers, and webhook headers, which can expose session or callback secrets in conversation history.

The contract explicitly requires the used payload, and sensitive input fields are documented. Disclosure depends on the user supplying secret-bearing values.

中

SKILL.md:127-131 SKILL.md:228-230

Target TLS Verification Disabled by Default

The request table documents skip_tls_verification with a true default, while the workflow advises keeping only necessary options. Requests that omit this option can accept invalid target certificates, allowing intercepted content or disclosure of supplied cookies and headers.

The insecure default is explicit in the parameter table, and examples do not override it. Actual provider behavior was not tested.

リスク要因

⚙️ 外部コマンド (50)

🌐 ネットワークアクセス (13)

SKILL.md:85 SKILL.md:33 SKILL.md:5 SKILL.md:32 SKILL.md:44 SKILL.md:54 SKILL.md:57 SKILL.md:65 SKILL.md:68 SKILL.md:74 SKILL.md:84 SKILL.md:85 SKILL.md:97

📁 ファイルシステムへのアクセス (13)

SKILL.md:52 SKILL.md:63 SKILL.md:83 SKILL.md:52 SKILL.md:63 SKILL.md:83 SKILL.md:5 SKILL.md:19 SKILL.md:5 SKILL.md:19 SKILL.md:52 SKILL.md:63 SKILL.md:83

🔑 環境変数 (16)

SKILL.md:52 SKILL.md:63 SKILL.md:83 SKILL.md:52 SKILL.md:63 SKILL.md:83 SKILL.md:17 SKILL.md:23 SKILL.md:45 SKILL.md:52 SKILL.md:56 SKILL.md:63 SKILL.md:67 SKILL.md:75 SKILL.md:83 SKILL.md:100

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/xcrawl-api-xcrawl-scrape/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/xcrawl-api-xcrawl-scrape/security.svg)](https://skillstore.io/skills/xcrawl-api-xcrawl-scrape?utm_source=security_passport_badge)

HTMLバッジ

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

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/xcrawl-api-xcrawl-scrape.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

xcrawl-api. (2026). xcrawl-scrape security audit report (audit version 1) [Author version 1.0.2]. Skillstore. https://skillstore.io/skills/xcrawl-api-xcrawl-scrape/audits/1

BibTeX形式の引用

@techreport{xcrawl-api-xcrawl-api-xcrawl-scrape-2026,
  author = {xcrawl-api},
  title = {xcrawl-scrape security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/xcrawl-api-xcrawl-scrape/audits/1},
  note = {Author version 1.0.2}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "xcrawl-scrape security audit report (audit version 1)"
version: "1.0.2"
type: report
authors:
  - name: "xcrawl-api"
date-released: "2026-10-17"
url: "https://skillstore.io/skills/xcrawl-api-xcrawl-scrape/audits/1"
identifiers:
  - type: other
    value: "skillstore:xcrawl-api-xcrawl-scrape: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

100

仕様準拠

作成できるもの

Collect Page Content for Research

Retrieve Markdown and links from a public source page, then request a separate summary when needed.

Extract Product Fields

Define product fields and accepted null values before requesting structured extraction from a product page.

Retrieve Rendered Page Evidence

Request a rendered screenshot with a defined viewport and inspect task status and API errors.

これらのプロンプトを試す

Fetch Page Markdown

Fetch [public URL] synchronously with XCrawl and return Markdown plus links. Enable target TLS verification and redact secrets from displayed payloads.

Extract Named Fields

Extract title, price, and currency from [product URL]. Allow null for missing values. Enable target TLS verification and redact secrets from displayed payloads.

Capture a Mobile Screenshot

Request a mobile screenshot of [public URL] with a 402 by 874 viewport. Enable target TLS verification and redact secrets from displayed payloads.

Run Asynchronous Schema Extraction

Scrape [public URL] asynchronously using [JSON Schema]. Enable target TLS verification. Poll with a retry limit until completion or failure. Redact secrets from displayed payloads.

ベストプラクティス

Define the authorized URL, required fields, accepted null values, and output formats before making a request.
Set request.skip_tls_verification to false, protect the local key file, and redact sensitive headers and cookies from displayed payloads.
Use bounded asynchronous polling and inspect terminal status, error details, and reported credit usage.

回避

Sending private URLs, cookies, or authentication headers to the hosted provider without authorization.
Relying on disabled target TLS verification or exposing secrets through raw payload output.
Polling indefinitely or treating extracted fields as verified facts without checking the source.

よくある質問

What must I configure before using this skill?

Create ~/.xcrawl/config.json with your XCRAWL_API_KEY and ensure your account has credits. Use curl or a suitable Node runtime.

Which output formats are documented?

The documented formats are HTML, raw HTML, Markdown, links, summary, screenshot, and JSON. Availability depends on the upstream API.

Can I extract specific fields?

Yes. The skill documents extraction prompts and JSON Schema options. Define required fields and how missing values should be handled.

How does asynchronous scraping work?

Create an asynchronous scrape, capture its task identifier, and poll the result endpoint until completion or failure. Set a polling limit.

Does this skill crawl an entire website?

No. It documents single-page scrape requests and result retrieval. Automatic link discovery and full-site crawl management are outside its scope.

What security precautions should I take?

Enable target TLS verification, protect the local key file, and redact secrets from displayed payloads. Only submit data you may share with XCrawl.

開発者情報

作成者

xcrawl-api

ライセンス

MIT

作者バージョン

v1.0.2

Skillstore リビジョン

リポジトリ

https://github.com/xcrawl-api/xcrawl-skills/tree/768158d9cd1e318742845b2eb7b9b37ae75f2c27/skills/xcrawl-scrape

参照

e7474dc9298cb48291ba8e94ae55fd5e402b4b85

メンテナンスの新しさ

2026/10/17

利用状況

0 ダウンロード · 0 閲覧

ファイル構成

建置 Firecrawl 單頁擷取

作成者 firecrawl

應用程式經常需要從一個已知 URL 取得乾淨內容。此技能會引導針對頁面擷取的聚焦 Firecrawl /scrape 整合。

コーディング＆開発表示

xcrawl-scrape

自分のエージェントでインストール

エージェントが読めるリソース

テストする

セキュリティ監査

確認済みのセキュリティ上の懸念 (2)

リスク要因

レポートリンクをコピー

Markdownバッジ

HTMLバッジ

埋め込みカード

APA形式の引用

BibTeX形式の引用

CITATION.cff

Skillstore スコア

作成できるもの

Collect Page Content for Research

Extract Product Fields

Retrieve Rendered Page Evidence

これらのプロンプトを試す

ベストプラクティス

回避

よくある質問

開発者情報

xcrawl-api のその他のスキル

xcrawl-search

xcrawl-map

xcrawl-crawl

xcrawl

関連スキル

pangolinfo-amazon-scraper

firecrawl

firecrawl-crawl

azure-ai-contentunderstanding-py

toon-format

firecrawl-build-scrape