Deep dives on AI security, agentic threat modeling, secure automation, and smart contract patterns.
Six years of blockchain auditing mapped to agentic security. Reentrancy, flash loans, oracle manipulation — the failure modes rhyme.
Four security problems in common AI automations — prompt injection, data leakage, credential management, and silent failures — with practical fixes.
STRIDE extended with three new threat categories for LLM agents — Confused Deputy, Context Pollution, and Trust Boundary Violation. Open spec, MIT licensed.