My lab just launched Khaos.

It’s a local-first CLI for testing AI agents against: - prompt injection - tool misuse / auth bypass - data leakage (PII) - resilience faults

  The examples are intentionally weak so you can break them quickly, then harden and re-test.

  pip install khaos-agent
  cd quickstart
  khaos discover .
  khaos start echo-assistant
  khaos run echo-assistant --eval security --verbose

  SDK: https://github.com/ExordexLabs/khaos-sdk
  Examples: https://github.com/ExordexLabs/khaos-examples

  I’d love blunt feedback on:

  1. CLI UX friction
  2. Missing attack classes
  3. What you’d need to adopt this in CI today