Google’s approach to security review with agents

How are security engineers at Google using agents to review code for vulnerabilities? How are they making the process more proactive and developer friendly? We will explore tools like Mantis, a multi-agent framework that automates security auditing and uses multi-step reasoning and a verification pipeline to minimize false positives. We will also demonstrate how to use Antigravity CLI with custom skills and hooks to perform interactive code reviews, catching vulnerabilities that may slip through "vibe-coded" or manually written features the moment the code is written. This session will cover how these patterns help developers embrace the "attacker mindset" to secure systems by spotting holes in controls far in advance of shipping to production. 🔗 Resources: Mantis blog → https://g.dev/ai/mantis-harness TDD security repo → https://g.dev/ai/secure-tdd-agent-framework Codelab for TDD with Antigravity → https://g.dev/ai/secure-agentic-coding Codelab for CodeMender → https://g.dev/ai/code-mender-cli Speaker: Mollie Pettit, Aron Eidelman, Nick Galloway Products Mentioned: Antigravity