Tutorials Intermediate
Gate Every PR With Claude Code Security Reviews
Wire Anthropic's /security-review and GitHub Action to catch SQLi, XSS and RCE before merge.
8 min read·Kodetra Technologies
2d agoGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
Tutorials Intermediate
Build a Prompt-Injection Eval for Claude Sonnet 5 Agents
Sonnet 5 claims better hijack resistance. Here's how to measure it yourself.
10 min read·Kodetra Technologies
Jul 2
Tutorials Advanced
Harden Your Local MCP Server Against AutoJack RCE
AutoJack turned a local MCP server into RCE. Harden yours with origin checks, auth, and allowlists.
9 min read·Kodetra Technologies
Jun 24
Tutorials Intermediate
Agentjacking Defense: Firewall Your AI Agent Tools
Build a Python trust-boundary firewall that stops prompt-injection attacks on your AI coding agent.
10 min read·Kodetra Technologies
Jun 23
Tutorials Intermediate
Claude Agent SDK: Lock Down Tools With Permission Hooks
Stop runaway tool calls and agent spawning using canUseTool, PreToolUse hooks and deny rules.
9 min read·Kodetra Technologies
Jun 12
Tutorials Intermediate
NVIDIA Verified Skills: Sign and Verify Agent Skills
Build a signed AI agent skill with a skill card using OpenSSF Model Signing, then verify it.
11 min read·Kodetra Technologies
May 27
Security Advanced
How to Secure an MCP Server Against Tool Poisoning
Harden MCP servers: kill tool poisoning, validate tokens, sandbox tools
9 min read·Kodetra Technologies
May 20
Security Intermediate
Passkeys + WebAuthn: Kill Passwords in Production
Implement phishing-resistant passkey login in Node.js: registration, signin, recovery.
12 min read·Kodetra Technologies
May 6
Tutorials Intermediate
Microsoft Agent Governance Toolkit: Secure AI Agents
Block agent attacks in <0.1ms with Microsoft's open-source runtime governance toolkit.
4 min read·Kodetra Technologies
May 1