AAPT · Red-Team Console

Break the Agent

Four AI agents. Four secrets. Each one falls to a different attack. Get it to leak — and learn exactly what AAPT tests automatically on real deployments.

aapt://secure-channel · target: acme-support-agent
LIVE
>

This is the tutorial.

Real agents get attacked through prompt injection, authority spoofing, multi-turn manipulation, and tool abuse — plus MCP servers and GraphQL APIs. AAPT runs 62 adversarial probes across all of it, automatically, and scores every finding.

See how AAPT works → Book a scoping call