Defense in Depth

AIAI SecurityLLM

AI Dark Arts (26): Defense in Depth Part Two, The Lines Around Agents, MCP and Model Files

14 September 2026·1153 words·6 mins

What OWASP recommendations 8 to 10 want you to restrict, who gets to write to memory, and what to verify on anything you connect from outside.

AIAI SecurityLLM

AI Dark Arts (25): Defense in Depth Part One, Which Layers Does Prompt Injection Defense Belong In?

13 September 2026·1762 words·9 mins

Walking the eleven recommendations in OWASP LLM01:2026 to see what each layer of prompt injection defense stops, and what picks it up when something gets through.

↑