by SalhaNabil · Agent Tool · ★ 55
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
| Stars | 55 |
| Forks | 1 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 48/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-19 |
| Created | 2026-05-19 |
| Platforms | browser, node |
| Est. Tokens | ~1k |
Stealth Chromium that passes every bot detection test. Not a patched config. Not a JS injection. A real Chromium binary with fingerprints modified at the C++ source level. Antibot systems score it as a normal browser — because it is a normal browser. Download Cloudflare Turnstile — 3 live tests passing (headed mode, macOS) Drop-in Playwright/Puppeteer replacement for Python and JavaScript.
These tools work well together with CloakBrowser for enhanced workflows:
Looking for a CloakBrowser alternative? If you're comparing CloakBrowser 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.
CloakBrowser: Anti-detect browser download, browser fingerprinting spoofing, multi-accounting tool, Canvas Web
Open-source stealth Chromium with engine-level fingerprint spoofing - de-Googled, drop-in Playwright, fully bu
Free, open-source anti-detect browser. A Chromium 155 fork that spoofs the fingerprint in C++ rather than with
Local-first anti-detect browser workspace: isolated profiles, AI agents, visual automation, Record & Replay, p
Anti-detect browser for AI agents and human operators. Isolated Chromium profiles (cookies, fingerprint, proxy
Free, open-source anti-detect browser profile manager: per-profile fingerprint, cookies and proxy, Camoufox an
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: