by AllAboutAI-YT · Agent Tool · ★ 66
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npm install -g surfagentTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
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 | 66 |
| Forks | 29 |
| Language | TypeScript |
| Category | Agent Tool |
| Quality Score | 73/100 |
| Open Issues | 1 |
| Last Updated | 2026-04-29 |
| Created | 2026-03-04 |
| Platforms | browser, node |
| Est. Tokens | ~14k |
surfagent Browser automation API for AI agents. Give any AI agent the ability to see, navigate, and interact with real web pages through Chrome. — two commands to give your agent a browser. surfagent connects to a local Chrome browser via CDP and exposes a simple HTTP API that returns structured page data — every interactive element, form field, link, and CSS selector — so AI agents can navigate...
Looking for a surfagent alternative? If you're comparing surfagent 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.
Claude Code skill for free Google AI Mode search with citations. Zero-config setup, persistent browser profile
Action library for AI Agent
Index the world's undocumented APIs
Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C
MCP server for free Google AI Mode search with citations. Query optimization, CAPTCHA handling, multi-agent su
An Autonomous AI Software Engineer
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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: