AI Security

OWASP Guide to Securing Agentic AI Applications: Best Practices for Trustworthy and Secure AI Systems

August 4, 2025 Lothar Schulz 0

Discover how architectural choices can be a defense in securing agentic AI systems. This comprehensive guide explores OWASP’s latest “Securing Agentic Applications” paper, covering everything from Sequential and Hierarchical architectures to the 15 critical threat categories facing autonomous AI applications. Learn practical implementation strategies, universal security principles, and how to build trust into your agentic AI systems from the ground up.

Flow Coding Security Analysis: Expert Personas for Rust Code Review

July 8, 2025 Lothar Schulz 0

This analysis examines a multi-persona AI prompt technique applied to Rust development, testing its effectiveness on a protein translation exercise. While the approach successfully transformed imperative code into functional pipelines and improved error handling, it revealed critical limitations including AI hallucination risks and test compatibility issues. For security-conscious teams, the technique offers valuable code quality improvements when integrated with human oversight and comprehensive validation processes.

Skip the Code: How AI Prompts Now Handle Tech Due Diligence Better Than Custom Scripts

June 15, 2025 Lothar Schulz 6

I built a Python solution in January for AI-powered supplier due diligence that required Jupyter notebooks and custom code. Now I’ve discovered something game-changing: modern AI systems like like Claude, ChatGPT, and Perplexity can handle complex tech assessments through simple prompts with zero technical setup. This post reveals the comprehensive prompt framework that delivers professional due diligence results without any coding, making AI-powered supplier assessments accessible to any CISO team.

Claude 4’s 25% Syntax Error Reduction

May 26, 2025 Lothar Schulz 0

Claude 4’s release brings significant improvements to AI-assisted coding that matter for security-conscious engineers. The coding platform Lovable reports a 25% reduction in syntax errors and 40% speed improvement in production environments.
While this doesn’t directly address semantic security issues like dependency confusion attacks, fewer syntax errors allow security reviewers to focus on logic and security issues rather than basic correctness, creating opportunities for more targeted security review.

Slopsquatting

April 24, 2025 Lothar Schulz 0

An AI-driven threat software engineers need to watch out for — when large language models hallucinate fake but plausible package names, and bad actors register them for malicious use. As AI-generated code becomes more common, verifying package names is no longer optional. Learn what slopsquatting is, why it matters, and how to protect your code.

Rust MCP Local Server: Bridging Rust Logic with AI Frontends

April 9, 2025 Lothar Schulz 0

Unlock the power of Rust for AI integrations! Learn how to use Rust-based logic with Model Context Protocol (MCP) to provide seamless context to AI frontends like Claude Desktop. While Rust doesn’t have an official MCP SDK yet, leveraging WebAssembly (Wasm) enables efficient integration with JavaScript environments. Explore how MCP standardizes communication with Large Language Models (LLMs). Whether you’re building custom AI workflows or connecting local data sources, this guide provides practical steps and solutions to get started.