browser-control — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

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 keon · Agent Tool · ★ 3.1k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is browser-control safe to install? View the security audit →

About browser-control

browser-control A tiny, fast Rust CLI that drives a real browser over the Chrome DevTools Protocol — built for coding agents. No LLM. No MCP requirement. No framework. Just compact, composable browser commands you can pipe from a shell. exposes a browser as a small, debuggable pipe: page snapshots, stable element refs, raw CDP, a background event watcher, and shell-runnable scripts. The coding agent stays the agent — just gives it hands and eyes. bash browser-control launch https://example.com browser-control snapshot # @e1 , @e2 , ... browser-control click @e2 browser-control eval 'document.tit

agentbrowser-automationllmrust

Quick Facts

Stars3,141
Forks209
LanguageRust
CategoryAgent Tool
LicenseMIT
Quality Score73.6308685107076/100
Last Updated2026-08-27
Created2016-12-21
Platformsbrowser, cli, rust
Est. Tokens~25k

Compatible Skills

These tools work well together with browser-control for enhanced workflows:

  • terminal-browser — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • rocketmq-rust — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • waku — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)
  • yek — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)

browser-control alternative? Top 6 similar tools

Looking for a browser-control alternative? If you're comparing browser-control 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.

  • nanobrowser by nanobrowser · ⭐ 13.6k

    Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API k

  • aichat by sigoden · ⭐ 10.3k

    All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, C

  • code2prompt by mufeedvh · ⭐ 7.6k

    A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token co

  • steel-browser by steel-dev · ⭐ 7.6k

    🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that le

  • cursor-talk-to-figma-mcp by grab · ⭐ 7.0k

    TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c

  • openpencil by ZSeven-W · ⭐ 5.9k

    The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. De

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is browser-control?

browser-control is A tiny, fast Rust CLI that drives a real browser over the Chrome DevTools Protocol — built for coding agents.. It is categorized as a Agent Tool with 3.1k GitHub stars.

What programming language is browser-control written in?

browser-control is primarily written in Rust. It covers topics such as agent, browser-automation, llm.

How do I install or use browser-control?

You can find installation instructions and usage details in the browser-control GitHub repository at github.com/keon/browser-control. The project has 3.1k stars and 209 forks, indicating an active community.

What license does browser-control use?

browser-control is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to browser-control?

The top alternatives to browser-control on Agent Skills Hub include nanobrowser, aichat, code2prompt. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools