by warterbili · Agent Tool · ★ 56
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is PerimeterX_RE safe to install? View the security audit →
| Stars | 56 |
| Forks | 9 |
| Language | JavaScript |
| Category | Agent Tool |
| Quality Score | 64/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-19 |
| Created | 2026-05-21 |
| Platforms | browser, claude-code, node |
| Est. Tokens | ~15k |
PerimeterX / HUMAN Security — SDK Reverse Engineering Pure-algorithm reconstruction of PerimeterX's / cookie chain — no browser, no automation framework. 中文 · Quick Start · How it works · Docs · AI Skill · License Given a target URL + AppID, this project rebuilds the PerimeterX collector POST chain entirely in pure math (Node.js) and emits a valid cookie.
These tools work well together with PerimeterX_RE for enhanced workflows:
Looking for a PerimeterX_RE alternative? If you're comparing PerimeterX_RE 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.
A self-healing scraper for hostile sites: broken selectors repair themselves, browser rendering kicks in when
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blo
Give your AI Agent the power to control Safari on macOS. No extensions, no separate browser.
Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP inter
Open-source stealth Chromium with engine-level fingerprint spoofing - de-Googled, drop-in Playwright, fully bu
Claude Code skill to bypass bot detection (Google CAPTCHA, etc.)
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: