skills.vishalvoidskills/vishalvoid
Technical & DevelopmentAdvanced

safe-browser

Build secure browser agents with domain allowlists.

Developer Setup

Setup & Installation

bash
npx skills add https://github.com/browserbase/skills --skill safe-browser

Overview

What This Skill Does

Constrains AI agents by enforcing a domain allowlist with Fetch interception, preventing raw shell or CDP access.

Application

When to use this Skill

Documentation

Show Skills.md file

Safe Browser

Build a local browser-agent demo where the generated runtime agent has exactly one browser capability: safe_browser. The tool owns the Playwright/CDP session, enables Fetch interception for all requests, and fails any request whose host is not allowlisted.

This skill is a builder guide. The skill itself is not the runtime boundary; the generated Claude Agent SDK app is.

When to Use

  • The user asks for a browser agent that must stay on an allowlisted site.
  • The user wants to demonstrate prompt-injection or link-following containment.
  • The user asks to build a scraper or browser workflow with domain policy.
  • The user asks for a Claude Agent SDK example first. Keep OpenAI Agents SDK variants out unless requested.

Default Approach

Use the Claude Agent SDK local template:

cp -R skills/safe-browser/templates/claude-agent-sdk /tmp/safe-browser-demo
cd /tmp/safe-browser-demo
npm install
cp ~/Developer/scratchpad/.env .env 2>/dev/null || true
node hn-scraper-demo.mjs
Lines 1 - 25 of 87

Recommendations

Explore other random skills

All skillsMy patterns