What security grade does openbrowser-ai have?

openbrowser-ai is graded CAUTION by AgentSkillsHub's rule-based security scan (SlowMist 11 red-flag categories). Has caution flags — fine for personal trials; review credentials and maintainer before brand or production use.

Is openbrowser-ai safe to install?

Security audit of billy-enrizky/openbrowser-ai · Agent Tool by billy-enrizky · ★ 235

⚠ CAUTION Basic audit · rule-based scan · SlowMist 11 red-flag categories

Use with caution — openbrowser-ai triggered warning flags in AgentSkillsHub's security scan. It may be fine for personal trials, but review its credential handling and maintainer before brand or production use.

What it is: OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

Red flags detected (2)

🚩 sudo usage
🚩 sensitive env vars

Audit summary

Security grade	⚠ CAUTION
Quality score	72/100
GitHub stars	235
Language	Python
License	MIT
Last updated	2026-07-07

Check before you install

What credentials does it ask for, and where are they stored?
Is the maintainer identifiable and the repo actively maintained?
Read the install scripts and network calls before trusting it.

Run a live scan → Full details & install 5-dimension deep audit

Related Agent Tool audits

Is superpowers safe? — SAFE · ★ 261.5k
Is AutoGPT safe? — SAFE · ★ 185.7k
Is ollama safe? — SAFE · ★ 176.9k
Is skills safe? — SAFE · ★ 173.9k
Is langflow safe? — SAFE · ★ 152.4k
Is langchain safe? — SAFE · ★ 142.6k

Browse all Agent Tool skills →

This is AgentSkillsHub's free basic audit: an automated rule-based scan covering SlowMist's 11 red-flag categories (credential exfiltration, obfuscated payloads, sandbox escape, prompt injection, and more) across 130,000+ open-source AI agent skills and MCP servers, refreshed every 8 hours. A CAUTION grade is a scan result, not a guarantee — deep 5-dimension audits (code · credentials · vendor · supply-chain · operational) are available for enterprise. Audited: 2026-07-26.