本文へスキップ
TakoAPI
スキル一覧に戻る

safe-web

adamnaghs 作

Web & Frontend Development
1.2kダウンロード数はclawskills.shが公開している値です
1スター
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Secure web fetch and search with **PromptGuard** scanning.

説明

このスキルでできること

Wraps web fetch and search operations with PromptGuard scanning to detect prompt injection attacks hidden in web content. Any page or search result that fails the scan is blocked before it enters the AI context window. Operates fail-closed: if scanning cannot run, the tool returns an error rather than unverified content.

Native web fetch tools return content without injection scanning, so malicious pages can silently alter AI behavior without detection.

使いどころ

  • Fetching articles from unfamiliar or untrusted URLs
  • Scraping competitor or news sites without exposing the AI to injected instructions
  • Searching the web during automated research pipelines
  • Processing user-supplied URLs in an AI agent workflow
  • Auditing web pages suspected of containing embedded injection attempts

ワークフロー例

入力

User asks: Summarize this article: https://unknown-blog.com/post

エージェント
  1. 1

    Runs 'safe-web fetch https://unknown-blog.com/post'

  2. 2

    Downloads the page and strips scripts and styles with BeautifulSoup

  3. 3

    Scans extracted text with PromptGuard

  4. 4

    Blocks content and returns a SHIELD report if injection patterns are detected

  5. 5

    Returns clean text to the AI if the scan passes

出力

Clean article text ready for summarization, or a security alert listing matched injection patterns and the blocked URL

要件

  • PromptGuard installed from clawhub.ai/seojoonkim/prompt-guard
  • Brave Search API key set as BRAVE_API_KEY environment variable (required for search command, free tier available at brave.com/search/api/)

インストール

clawhub install adamnaghs/safe-web

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク