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 idan-rubin · Codex Skill · ★ 75
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is browserclaw safe to install? View the security audit →
The browser tool, not the agent. You bring the brain. The AI-native browser automation library — born from OpenClaw, built on Playwright, embeddable in any TS/Node agent loop. Snapshot + ref targeting: no CSS selectors, no XPath, no vision model — just numbered refs that map to interactive elements. Most other tools in this space ship a complete AI agent: they take your task, own the LLM loop, decide what to click, and click it. Great — until you already have an agent. Then you've got two brains fighting over who's in charge. browserclaw is just the eyes and hands. Call and get an AI-readable text tree where every interactive e
| Stars | 75 |
| Forks | 7 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 62.9500266918046/100 |
| Last Updated | 2026-09-30 |
| Created | 2026-02-08 |
| Platforms | browser, node |
| Est. Tokens | ~23k |
These tools work well together with browserclaw for enhanced workflows:
Looking for a browserclaw alternative? If you're comparing browserclaw with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blo
One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local
让 Agent 直接操作真实 Chrome 的 MCP 服务，支持页面扫描、CDP、截图与物理输入
OpenClaw skill for scraping any URL using the Decodo Web Scraping API.
CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.
All-in-one MCP server that can connect your AI agents to any native endpoint, powered by UTCP
Explore other popular codex skill tools:
browserclaw is The AI-native browser automation library. Snapshot + ref targeting — born from OpenClaw, built for agents, by agents.. It is categorized as a Codex Skill with 75 GitHub stars.
browserclaw is primarily written in TypeScript. It covers topics such as accessibility, ai, ai-agent.
You can find installation instructions and usage details in the browserclaw GitHub repository at github.com/idan-rubin/browserclaw. The project has 75 stars and 7 forks, indicating an active community.
browserclaw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to browserclaw on Agent Skills Hub include camofox-mcp, Uni-CLI, agent-browser-mcp. 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: