No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by pmbstyle · Agent Tool · ★ 74
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is gemini-browser-agent safe to install? View the security audit →
Gemini Browser Agent A research experiment and browser automation project scaffolding. Run agent tasks right in your Chrome browser. Overview Gemini Browser Agent is an automation agent that bridges a Chrome extension with Google’s Gemini Computer Use API. It observes the active tab, exchanges screenshots and events with the model, and performs actions directly in your own browser, no sandbox or virtual machine required. Setup Install Python 3.10+ and Chrome (or Chromium-based) browser. Clone this repository and open a terminal in the project directory. (Optional) Create a virtual environment: Run the setup helper to install dependencies and scaffold : Visit to create a Gemini API key, then place it in the generated file as . Usage Start the Python WebSocket bridge: Open Chrome and navigate to . Enable Developer mode, choose Load unpacked, and select the directory from this project. Open the sidebar, click
| Stars | 74 |
| Forks | 18 |
| Language | JavaScript |
| Category | Agent Tool |
| Quality Score | 70.0549171033774/100 |
| Last Updated | 2025-10-23 |
| Created | 2025-10-23 |
| Platforms | browser, gemini, node |
| Est. Tokens | ~2k |
These tools work well together with gemini-browser-agent for enhanced workflows:
Looking for a gemini-browser-agent alternative? If you're comparing gemini-browser-agent with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simp
OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a Cod
◉ Universal Intelligence: AI made simple.
Claude Code skill for free Google AI Mode search with citations. Zero-config setup, persistent browser profile
Index the world's undocumented APIs
AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app
Explore other popular agent tool tools:
gemini-browser-agent is A browser agent with a Google Chrome extension that can work in your browser. Based on Google Gemini 2.5 computer use model.. It is categorized as a Agent Tool with 74 GitHub stars.
gemini-browser-agent is primarily written in JavaScript. It covers topics such as ai-agents, ai-browser-automation, browser-automation.
You can find installation instructions and usage details in the gemini-browser-agent GitHub repository at github.com/pmbstyle/gemini-browser-agent. The project has 74 stars and 18 forks, indicating an active community.
The top alternatives to gemini-browser-agent on Agent Skills Hub include open-browser-use, openbrowser-ai, universal-intelligence. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: