The CybeDefend blog.
How to secure the code agents write.
Research, guides and field notes. A new article every week.
All posts
36 articles- Security
Open-Source SAST Tools in 2026: 20 Checked on GitHub, by Language
- Security
How to Give Claude Code Your Business Context, Not Just Your Conventions
- Security
Are Claude Code Skills Safe? How to Vet a Skill or Plugin Before You Install It
- Security
Claude Code --dangerously-skip-permissions: What It Skips, and What Still Blocks
- Security
Does Codex Send My Code to OpenAI? Privacy, Training and Data Controls
- Security
How Much Does an AI Code Security Tool Cost in 2026? Prices, Models and ROI
- Security
Antigravity's Sandbox Protects Your Laptop, Not Your Codebase
- Research
Your CLAUDE.md Works on the Rules You Did Not Need
- Security
Codex danger-full-access, --yolo and Unsafe Mode: What Each Flag Disables
- Research
Your Agent Never Escaped the Sandbox. It Did Not Need To.
- Research
Nobody Is Reviewing Your Agent's Pull Requests
- Research
Your Model Got Smarter. Your Code Did Not Get Safer.
- Security
Instruction File Injection: How AGENTS.md and CLAUDE.md Hijack Coding Agents
- Compliance
What Is an AI-BOM? The AI Bill of Materials the EU AI Act Assumes You Already Have
- Security
What Is Slopsquatting? Slopsquatting vs Typosquatting, and the HalluSquatting Attack
- Security
Can AI Agents Find and Auto-Fix Vulnerabilities? Tools, Evidence and Limits
- Security
The Best AI Code Security Tools in 2026: 13 Tools Compared by Need
- Security
Is AI-Generated Code Safe? What the 2026 Data Shows, and What Scanners Miss
- Security
How to Add Security to Your AI Coding Workflow (Without Slowing It Down)
- Security
AI Vulnerability Remediation: Giving Coding Agents Live Access to Every Finding
- Security
How to Secure an Application in 5 Minutes With Your AI Agent
- Security
AI Coding Agent Security: The Agent-Time Model
- Research
Business Logic Flaws in AI-Generated Code: Why Your Scanner Is Blind
- Security
MCP Security: Tool Poisoning, Prompt Injection, and How to Lock Down Agent Tools
- Security
Vibe Coding Security: The Risks You Ship With, and How to Catch Them
- Security
Is Windsurf Safe to Use? Security Risks, Controls and Best Practices
- Security
Is Claude Code Safe to Use? Security Risks, Controls and Best Practices
- Security
Is Cursor Safe to Use? Security Risks, Controls and Best Practices
- Release
Rust SAST is mostly theatre. We just shipped the real one.
- Security
Is GitHub Copilot Safe to Use? Security Risks, Controls and Best Practices
- Security
Is OpenAI Codex Safe to Use? Security Risks, Sandbox Modes and Best Practices
- Product
VibeDefend Just Shipped. Your AI Agent Has New Rules, Installed in One Command.
- Research
Why your scanner reports 1,200 vulnerabilities and only 12 are real
- Research
The $0 Shopping Cart: Why Your "All-Green" SAST Report Is Lying To You
- Research
The Evolution of Secure by Design in the AI Era
