What Changes When Agents Write the Code: Gabriel (Yalo) on Software Factory Security

Gabriel, Staff Security Engineer at Yalo, joins us live at AI Security Summit in San Francisco to explain how you secure a software factory whose product is other agents. Yalo builds AI sales agents for its customers, and its newest tool is an agent that builds agents, so securing that one agent means securing the factory. Gabriel walks through the layers: role-based access and authorization on APIs and services that predate agents, so anyone prompting the factory gets only the scope they should have; agent firewalls at the edge that redact PII and block off-limits conversations in microseconds, backed by asynchronous LLM judges; red teaming against prompt injection and the OWASP LLM Top 10; and scanning every skill for leaked credentials and exfiltration paths. He's also candid about what feels like a hard problem to solve: blocking a misbehaving agent at runtime.