by pmbstyle · Agent Tool · ★ 75
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: browser-use, Playwright MCP & AI Browser Agents
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 75 |
| Forks | 19 |
| Language | JavaScript |
| Category | Agent Tool |
| Quality Score | 70/100 |
| Last Updated | 2025-10-23 |
| Created | 2025-10-23 |
| Platforms | browser, gemini, node |
| Est. Tokens | ~2k |
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.
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.
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-powered annotations for localhost development. Create visual feedback on your apps and let AI coding agents
Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: