browser-agent-safety-playbook

Name: browser-agent-safety-playbook
Author: uygnoey

SKILLWorkflowcommunity

v0.0.0uygnoeyMITUpdated 3mo agoSource →

Apply a safety-first checklist when using Claude in a browser extension: site permissions, action confirmations, autonomous-mode guardrails, and prompt-injection defenses.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →

2Repo stars

1Clients

1Formats

3mo agoLast update

Skill

Authoruygnoey

Version0.0.0

LicenseMIT

CategoryWorkflow

Formatsskill.md

PromptNot published

Compatibility

Claude✓ Supported

Cursor—

Copilot—

ChatGPT—

Gemini—

About

Apply a safety-first checklist when using Claude in a browser extension: site permissions, action confirmations, autonomous-mode guardrails, and prompt-injection defenses.

Keywords

skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.

Topics

Related in browser automation & scraping

microsoft/playwrightPlaywright is a framework for Web Testing and Automation. It allows testing Chromium, Fire
D4Vinci/Scrapling🕷️ An adaptive Web Scraping framework that handles everything from a single request to a
ChromeDevTools/chrome-devtools-mcpChrome DevTools for coding agents
io.github.bytedance/mcp-server-browserMCP server for browser use access
bytedance/UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Inf
microsoft/playwright-mcpPlaywright MCP server
agent-deviceMobile app automation and verification for AI coding agents. CLI, MCP server, and typed No
yusufkaraaslan/Skill_SeekersConvert documentation websites, GitHub repositories, and PDFs into Claude AI skills with a