Brooks McMillin

Infrastructure Security Engineer at Dropbox

I lead a team focused on AI agent security, LLM development tooling, and securing production AI systems. We build the frameworks that help engineers ship AI features safely.

Building Secure Agentic Systems: The Six Layers

Six layers of security architecture for running LLM agents as daily drivers — every design decision with production stats and companion code.

Read Article

Current Focus

AI Agent & Infrastructure Security

Making sure AI agents don't do things they shouldn't, and giving engineers the tools to ship AI features without creating new attack surface.

  • Sandboxing, permissions, and runtime controls for autonomous AI agents
  • LLM security tooling that fits into existing developer workflows
  • Threat modeling for MCP, multi-agent systems, and tool-use patterns in production
  • Identity, access control, and data protection for AI/ML infrastructure

Featured Projects

Agent Framework

production
PythonModel Context ProtocolOAuth 2.0Anthropic Claude

Framework for building LLM agents with MCP, OAuth 2.0 with PKCE, persistent memory, and extensible tool architecture. Runs 19 agents in production.

  • Runs 19 specialized agents as daily drivers
  • Full OAuth 2.0 with PKCE and dynamic client registration

TaskManager

production
AstroNode.jsPostgreSQLOAuth 2.0

Task management platform with a full OAuth 2.0 auth server, Python SDK, and MCP server so my AI agents can manage tasks too.

  • Full OAuth 2.0 authorization server with PKCE support
  • Security testing suite with Vitest
GoPythonGSMSerial Communication

Send and receive SMS through GSM modems. Implementations in both Go and Python, with CLI tools for testing and operational use.

  • Cross-platform GSM modem interface (Go + Python)
  • Interactive CLI chat interface
PythonGormapiAnthropic Claude

Tools for managing research papers on reMarkable tablets, with AI-powered classification and automated organization.

  • AI-powered research paper classification
  • Zero-config rmapi binary management
View All Projects

Recent Appearances

[un]prompted · March 2026 · San Francisco, CA

Real patterns and failures from building specialized agents with shared infrastructure, covering capability bounding, prompt injection detection, memory isolation, and OAuth device flow

The Secure Disclosure Podcast · March 2026 · Mesa, AZ

Discussion on malicious MCP servers, recurring security mistakes in AI tooling, prompt injection persistence, and practical strategies for safe AI deployment

CactusCon · February 2026 · Mesa, AZ

Security audit of MCP servers and their OAuth implementations, demonstrating that 90% of vulnerabilities reflect longstanding security principles amplified by AI agents

Dropbox (Internal Tech Talk) · February 2026

A three-layer defensive framework for catching security mistakes introduced by LLM-assisted code generation before they reach production

View All Appearances

Let's Connect

Interested in AI security, collaboration, or speaking? I'd like to hear from you.

More About Me