I've been building a zero-trust local firewall for AI coding agents (like Cursor, Claude Code, etc.).
The problem I m trying to solve is that LLMs constantly hallucinate package names. Bad actors are starting to register those fake packages with malicious code (slopsquatting). So if your AI agent autonomously runs `npm install` or `pip install` on a hallucinated package, your machine gets compromised instantly.
I just spent weeks updating my tool (Agentinel) to natively intercept terminal commands across JS, Python, and Rust in under 1 millisecond. It uses a massive offline vulnerability database to block the AI from pulling malware before the shell even executes it.
Because your AI loves slopsquatting. The zero-cost, locally-run firewall for AI agents. Designed to instantly intercept hallucinated and malicious packages across JavaScript, Python, and Rust before your terminal runs them.
Because your AI loves slopsquatting. The zero-cost, locally-run firewall for AI agents. Designed to instantly intercept hallucinated and malicious packages across JavaScript, Python, and Rust before your terminal runs them.
Because your AI loves slopsquatting, Agentinel is a zero-cost, locally-run package guardrail for autonomous AI coding agents (like Claude Code and Cursor). It integrates directly at the hook level to intercept hallucinated and malicious npm packages before they execute, checking them against a 60,000+ threat database in under 2ms
