safe-web
adamnaghs 제작
Web & Frontend Development요약
Secure web fetch and search with **PromptGuard** scanning.
설명
이 스킬이 하는 일
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.
사용 시점
- 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
예시 워크플로
User asks: Summarize this article: https://unknown-blog.com/post
- 1
Runs 'safe-web fetch https://unknown-blog.com/post'
- 2
Downloads the page and strips scripts and styles with BeautifulSoup
- 3
Scans extracted text with PromptGuard
- 4
Blocks content and returns a SHIELD report if injection patterns are detected
- 5
Returns clean text to the AI if the scan passes
Clean article text ready for summarization, or a security alert listing matched injection patterns and the blocked URL
요구 사항
- 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/)
설치
clawhub install adamnaghs/safe-webCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.