By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Attack trees and kill chains

Attack trees break an attacker goal into the alternative and combined steps needed to reach it, so you can see where one control cuts off many paths. Kill chain models apply the same idea over time, and now describe how a prompt injection escalates into persistence, lateral movement, and data theft.

Read in this order

  1. ArticleAttack Trees (Bruce Schneier)Start here: the original, short explanation of attack trees from the person who named them.
  2. PaperThe Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery MechanismShows a kill chain applied to prompt injection, step by step.
  3. Open sourceDeciduous: security decision tree generatorBuild and share your own decision trees with a ready-made generator.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.