Skip to main content
Work

Selected Work

Standards authorship, benchmarks leadership, AI enablement programs, and applied AI security work at the Center for Internet Security.

Published CIS Companion Guides

Public · Link Pending Principal Co-author

CIS Controls v8.1 Model Context Protocol (MCP) Companion Guide

Center for Internet Security · April 2026

Translated MCP-specific risks into practical guidance mapped to all 18 CIS Controls. Covers MCP clients, servers, tools, resources, prompts, authorization, least privilege, auditability, confused deputy risk, tool boundaries, third-party server governance, and secure configuration considerations. Co-authored with Shreyans Mehta (Cequence).

What it demonstrates

Andrew's ability to translate a fast-moving AI protocol into practical security guidance aligned with an established control framework — combining protocol-level technical depth with clear, actionable implementation guidance.

MCP Security CIS Controls Authorization Secure Configuration Tool Boundaries
Public · Link Pending Collaborator

CIS Controls v8.1 AI and LLM Companion Guide

Center for Internet Security · April 2026

Collaborated on the AI and Large Language Models Companion Guide, contributing to practical guidance on LLM security, model-layer risk, inference behavior, data handling, monitoring, and CIS Controls mapping for enterprise AI environments.

What it demonstrates

Andrew's ability to contribute meaningfully to practical AI security and adoption guidance for enterprise AI systems — bridging model-layer technical risk with organizational controls.

LLM Security Prompt Injection Data Handling CIS Controls Model Risk
Public · Link Pending Collaborator

CIS Controls v8.1 AI Agents Companion Guide

Center for Internet Security · April 2026

Collaborated on the AI Agents Companion Guide, contributing to guidance on agent autonomy, tool invocation, memory, planning, human approval gates, monitoring, and secure integration of agentic AI workflows into enterprise environments.

What it demonstrates

Andrew's ability to connect agentic AI risk to practical security controls and enablement guidance — making emerging multi-agent and autonomous AI risk patterns actionable for security practitioners.

Agentic AI Human Oversight Tool Invocation CIS Controls Multi-Agent

Authorship note: The MCP Companion Guide lists Andrew Dannenberger as a Principal Author alongside Shreyans Mehta (Cequence). The AI/LLM and AI Agents Companion Guides are collaborative CIS publications; Andrew contributed as a collaborator/editor. Authorship credits reflect publicly available acknowledgment pages. This personal website does not represent CIS.

Active Initiatives

In Development AI Benchmarks Lead / Community Coordination / Roadmap Support

CIS AI Benchmarks Community

Center for Internet Security · Ongoing

Leading CIS AI Benchmarks Community work to advance practical guidance for securing emerging AI technologies. Responsible for scope definition, community coordination, feedback cycles, and publication roadmap — working with practitioners to translate AI security risk into benchmark-style, auditable guidance.

What it demonstrates

Leadership at the intersection of cybersecurity standards, AI security, and practitioner-focused implementation — coordinating across stakeholders to produce guidance that organizations can actually act on.

CIS Benchmarks AI Security Community Standards Leadership
Scheduled Benchmark Development Leadership / MCP Security Standards Work

CIS MCP Benchmark

Center for Internet Security · Scheduled

Leading development of a CIS MCP Benchmark — translating MCP-specific risk across clients, servers, tools, resources, prompts, authorization, least privilege, auditability, confused deputy patterns, and secure configuration into benchmark-style recommendations with audit and remediation thinking.

What it demonstrates

Leadership in translating MCP security risk into prescriptive, benchmark-ready guidance — demonstrating both protocol-level understanding and the practitioner discipline required to write auditable security benchmarks.

MCP CIS Benchmarks Secure Configuration Audit Standards
Internal AI Assistant Prototype and MVP Leadership

CIS QuickAssist / AI Chatbot Initiative

Center for Internet Security · 2023 – Present

Built and advanced a documentation-focused AI assistant from proof of concept toward minimum viable product. Created a knowledge-base chatbot for internal support workflows and public documentation, maintained AI research resources tracking emerging advances, risks, and organizational implications.

What it demonstrates

Andrew's ability to move AI tooling from initial concept to a practical, support-facing use case — combining technical implementation with a clear understanding of where AI adds value in knowledge management and customer workflows.

AI Chatbot RAG Documentation MVP Knowledge Base
Internal MCP Server Development and Customer-Facing AI Integration Support

SecureSuite Platform MCP Concepts

Center for Internet Security · Ongoing

Developing MCP server concepts for the SecureSuite Platform. Engaging customers and technical stakeholders on secure integration patterns, governance, supportability, and AI product enablement — connecting MCP security standards to real platform and customer workflows.

What it demonstrates

Andrew's ability to connect AI security standards to real platform and customer contexts — bridging standards work and engineering concepts to practical product adoption guidance.

MCP SecureSuite Product Enablement Customer Engagement Integration
Internal Secure AI Enablement Lead / Presenter / Facilitator

AI Office Hours and Internal Enablement Programs

Center for Internet Security · Ongoing

Designed and leads recurring AI Office Hours and internal enablement sessions for beginner and advanced audiences. Converts complex AI security and adoption topics into practical workflows, exercises, and clear guidance — focusing on safe AI use, prompt design, workflow improvement, and responsible internal experimentation.

What it demonstrates

Andrew's ability to teach complex AI concepts clearly and practically to diverse audiences — a direct expression of the communication and adult-learning background that informs all his standards and enablement work.

AI Enablement Training Safe AI Adoption Facilitation Prompt Design
Public · Link PendingInternalIn DevelopmentScheduled
Personal website — This is a personal professional portfolio. Work marked Internal represents real initiatives; confidential implementation details are not disclosed. This website does not represent CIS or any employer.