HomeDocsBlogDownload
๐Ÿ”’
Security March 18, 2026 ยท 8 min read

The Hidden Risk of MCP Tools: Why Your AI Agent Could Be a Backdoor

We analyzed 2,000+ MCP tools on npm and found that 14% request network permissions they don't need, 6% contain obfuscated code, and 2% attempt to exfiltrate environment variables. Here's what we found and how to protect yourself.

๐Ÿš€
Product March 12, 2026 ยท 4 min read

ClaudeArmor v2.4.1: Forensic AI Threat Reports & Custom Threat Policies

The latest release brings Forensic AI threat explanations, custom organization threat policy support, and a 42% scan speed improvement.

๐Ÿ”‘
Guide February 28, 2026 ยท 6 min read

How to Prevent API Key Leaks in AI-Generated Code

AI coding agents are great at writing code โ€” and accidentally committing your secrets. Here's a practical guide to keeping your keys safe.

๐Ÿ—๏ธ
Engineering February 15, 2026 ยท 10 min read

Inside Our Zero-Trust Micro-Sandbox Architecture

An overview of how ClaudeArmor isolates untrusted MCP tools and agent commands inside a strict execution boundary.

๐Ÿ“Š
Research January 22, 2026 ยท 12 min read

State of AI Agent Security 2026: A Comprehensive Report

We surveyed 500 developers and analyzed 10,000 repositories to understand the security landscape of AI-assisted development.

โš™๏ธ
Tutorial January 8, 2026 ยท 5 min read

Setting Up ClaudeArmor in Your CI/CD Pipeline

Step-by-step guide to integrating ClaudeArmor scans into GitHub Actions, GitLab CI, and CircleCI for automated security checks on every PR.