Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

safe-web

bởi adamnaghs

Web & Frontend Development
1.2kLượt tải do clawskills.sh công bố
1Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

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

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

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

AGENT
  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

ĐẦU RA

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

Yêu cầu

  • 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/)

Cài đặt

clawhub install adamnaghs/safe-web

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết