opena2a-org

AI Browserguard — Testing skill for Claude Code

Testing community

A firewall for browser agents.

How to install AI Browserguard

This entry records only its repository, not the path inside it, so there is no exact command to give. Open opena2a-org/ai-browserguard and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Browserguard does

A firewall for browser agents. Chrome extension that detects, monitors, and controls AI agents in your browser. Identifies Playwright, Puppeteer, Selenium, Anthropic Computer Use, and OpenAI Operator without the agent identifying itself.

Alternatives in Testing

Opencode Skill Creator — OpenCode skill for creating, testing, and optimizing other OpenCode skills 157 ★
Publish Speckit Ext — Release the spec-kit extension (companion) to a GitHub release for catalog/--from install 85 ★
GEMINI.md - Spec-Flow For Gemini CLI — Spec-Flow Workflow Kit: Transform product ideas into production releases via spec-driven development 73 ★

README

AI Browser Guard

[![Status: beta](https://img.shields.io/badge/status-beta-yellow)](STATUS.md) [![Chrome Web Store](https://img.shields.io/chrome-web-store/v/ojphpdmabflmcjhglfogmkdgchkncikf)](https://chromewebstore.google.com/detail/ojphpdmabflmcjhglfogmkdgchkncikf) [![Build](https://github.com/opena2a-org/AI-BrowserGuard/actions/workflows/ci.yml/badge.svg)](https://github.com/opena2a-org/AI-BrowserGuard/actions/workflows/ci.yml) [![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)

**[OpenA2A](https://github.com/opena2a-org)**: [CLI](https://github.com/opena2a-org/opena2a) · [HackMyAgent](https://github.com/opena2a-org/hackmyagent) · [Secretless](https://github.com/opena2a-org/secretless-ai) · [AIM](https://github.com/opena2a-org/agent-identity-management) · **Browser Guard** · [DVAA](https://github.com/opena2a-org/damn-vulnerable-ai-agent)

[Website](https://opena2a.org/aibrowserguard) · [Privacy policy](https://opena2a.org/aibrowserguard/privacy) · [Discord](https://discord.gg/uRZa3KXgEn)

Chrome extension that detects and monitors AI agents operating in your browser (Playwright, Puppeteer, Selenium, Anthropic Computer Use, and OpenAI Operator) without requiring the agent to identify itself. For in-page and injected automation it can also block scripted navigations, form submissions, and new-tab opens (best-effort, in the page realm). Under a delegation that does not permit downloads, it can cancel a download that Chrome reports starting in an agent's tab, for every kind of agent, including one you start there. Beyond that it **cannot** block external automation frameworks that drive the browser over CDP; against those, AI Browser Guard provides detection, alerting, and a kill switch that closes the tab, not per-action enforcement. See [Scope of enforcement](#what-it-does).

[Install from Chrome Web Store](https://chromewebstore.google.com/detail/ojphpdmabflmcjhglfogmkdgchkncikf)

An AI agent takes over a tab. AI Bro