SADF holds the model constant and finds a 2.6x compromise-rate spread across orchestration frameworks.

Julie Brunias presented the Synthetic Agent Deception Framework at DEF CON 34's AI Village: 5,119 evaluation rows, eight architectures, 32 payloads. Keeping Claude Sonnet fixed and swapping only the wrapper moved Agent Compromise Rate from 11.9% (CrewAI) to 31.1% (SmolAgents), with direct API at 15.5%, LangChain 18.1%, AutoGen 20.0%. SmolAgents' verbose reasoning traces push intermediate tool output back into context, driving 64% Context Boundary Violation. Your framework choice is a security decision.