Blog | Brooks McMillin - AI Security Researcher

February 26, 2026

Does Your System Prompt Actually Stop Prompt Injection? We Tested 10,000 Times to Find Out

An empirical study of 10,080 prompt injection attempts across 8 models, 6 defense strategies, and 7 attack types. The results challenge common assumptions about prompt-level defenses.

#security#AI#LLM#prompt-injection#ai-security#benchmark

January 28, 2026

Defense in Depth for AI-Assisted Development: Pre-commit Hooks, Review Agents, and CI That Catch LLM Mistakes

Practical strategies for safer AI-assisted development: automated review agents, layered security checks, and context management that prevents catastrophic mistakes.

#security#AI#LLM#ci-cd#pre-commit#code-review#MCP

September 7, 2025

The Call is Coming from Inside the House: When your Agentic Coder Writes Dangerous Code

An introduction to the flaws in security testing for AI-generated code.

#security#AI#LLM#vibe-coding#ai-security

AI Security Research Blog

Does Your System Prompt Actually Stop Prompt Injection? We Tested 10,000 Times to Find Out

Defense in Depth for AI-Assisted Development: Pre-commit Hooks, Review Agents, and CI That Catch LLM Mistakes

The Call is Coming from Inside the House: When your Agentic Coder Writes Dangerous Code