Trust BoundaryAI security research, red teaming, agentic development, and security field notes.https://sandkcampbell.com/Breaking Agents to Build Better Ones: LLM01 Prompt Injectionhttps://sandkcampbell.com/blog/breaking-agents-llm01-prompt-injection/https://sandkcampbell.com/blog/breaking-agents-llm01-prompt-injection/A hands-on RAG prompt-injection lab for learning OWASP LLM01:2025, measuring attack success rate, and testing a simple spotlighting defense.Thu, 14 May 2026 00:00:00 GMTSupply Chain Attacks on AI Tooling: Lessons from Shai-Huludhttps://sandkcampbell.com/blog/shai-hulud-ai-tooling/https://sandkcampbell.com/blog/shai-hulud-ai-tooling/A field report on the npm worm that targeted ~/.claude/, the three scanners I built in response, and what AI infra security needs next.Wed, 13 May 2026 00:00:00 GMTWelcomehttps://sandkcampbell.com/blog/welcome/https://sandkcampbell.com/blog/welcome/What this site is and what's coming.Wed, 13 May 2026 00:00:00 GMT