ALT Promotional graphic for The AI Security Summit. On the left, there is a conference badge with a black-and-white photo of a smiling person wearing glasses and a t-shirt. The badge is labeled “SPEAKER” in bold yellow text. On the right, large yellow text says “JOIN ME” with the event dates “October 22–23” and the location “San Francisco” indicated by a pin icon. At the bottom, the event website is listed: AISECURITYSUMMIT.COM. The design uses black, gray, and bright yellow colors with diagonal stripe patterns in the background.

ALT From a security perspective, these are the most important questions to ask when choosing a framework: Is the framework sufficiently secure by default? Most current frameworks aren’t. Furthermore, they operate on different abstractions (e.g., ADK exposes a transfer_to_agent tool), which differ in their security properties. Does the framework provide sufficient visibility and control over the context window and control flow? Many AI engineers argue that frameworks should not be used because they force you to cede visibility and control over the context window and control flow to the framework (e.g., the use of append_instructions in ADK). Not controlling your prompts and context window results in attacks like prompt injection. Not controlling your control flow results in attacks like MAS hijacking. Refer to factors 2, 3, and 8 of 12-factor agents, a set of principles for building reliable AI applications. Does the framework provide sufficient support for different security mechanisms?

ALT anamorpher demo