Blue Team Con 2026

Name: Teaching AI to Analyze Malware: How to Encode Practitioner Expertise into an MCP Server
Start: 2026-09-12T10:30:00-0500
End: 2026-09-12T11:30:00-0500

Teaching AI to Analyze Malware: How to Encode Practitioner Expertise into an MCP Server

Saturday September 12, 2026 10:30am - 11:30am CDT

Swissôtel Chicago

AI agents can reason about suspicious files, plan multi-step investigations, and write custom deobfuscation code when standard tools fall short. But generic models produce shallow, unreliable results because they lack practitioner knowledge about which tools to use and when, and access to the tools themselves.
Without domain expertise, an AI agent doesn't know that, for example, capa exit codes follow non-standard conventions, that YARA match counts require context to interpret, or that GetProcAddress appears in virtually every Windows program and is not inherently suspicious. Without tool access, it can only comment on malware but cannot investigate it.
This talk walks through my experience of building an open source MCP server, a standardized interface that connects AI agents to external tools, that bridges both gaps simultaneously. The server connects AI agents to my open source REMnux malware analysis toolkit, encoding practitioner knowledge into tool workflow sequencing and output interpretation. The server runs analysis at three depth levels, and manages context budgets when tool output exceeds approximately reasonable values by automatically switching to summary mode while preserving key findings.
The server also counteracts confirmation bias. Generic AI agents tend to label every API call as suspicious and every string as an indicator of compromise. The server's neutral framing prompts agents to consider benign explanations before concluding malicious intent. This is a critical safeguard when the AI chains dozens of tool calls without human review at each step.
Against real-world samples, the resulting system completed full investigations in about 10 minutes with 25-30 automated tool calls. In one case during my experimentation, the AI agent wrote custom Python to reconstruct a PE from file fragments. In another, it reverse-engineered a proprietary archive format and adapted when initial analysis approaches failed.
The talk covers what worked, what failed, and what surprised me. It addresses the security model required when AI agents have tool access, including prompt injection risks from malicious content in analyzed samples, container isolation as the primary security boundary, and data flow considerations.
Attendees leave with a reproducible pattern for encoding domain expertise into MCP servers, applicable to incident response, cloud forensics, network analysis, or any domain with specialized tools and practitioner workflows.

Speakers

Lenny Zeltser

Faculty Fellow, SANS Institute

Lenny Zeltser is a cybersecurity executive with deep technical roots, product management experience, and a business mindset. He has built security products and programs from early stage to enterprise scale. He is also a Faculty Fellow at SANS Institute and the creator of REMnux, a... Read More →

Saturday September 12, 2026 10:30am - 11:30am CDT
Swissôtel Chicago 323 E Wacker Dr, Chicago, IL 60601, USA

Talk

Audience Intermediate
Subject Threat Intel and DFIR
global Y

Tickets

Success you have shared X tickets.

Blue Team Con 2026

Lenny Zeltser

Get help with the event

Choose your checkout method

Success you have shared X tickets.

Blue Team Con 2026

Lenny Zeltser

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Get help with the event