World Congress 2026 Europe • Jul 10, 2026 • Session details

Agent Smith Gets Hardware: Autonomous IoT Hacking From Debug Port to Cloud API

Marc Plogas

Think a factory reset secures your discarded smart plug? Watch an autonomous AI agent exploit hidden debug ports to instantly extract lingering Wi-Fi passwords and cloud tokens.

Pause
Mute Enter Fullscreen
#1 about 3 min

Introduction to autonomous hardware hacking agents

How an AI agent autonomously hacked smart filament tags without prior training.

#2 about 4 min

Architecture of the AI hardware hacking system

Structuring Claude Code with project and tool MCPs to enforce physical safety tiers.

#3 about 2 min

Evaluating the Gosund v2 smart plug target

Identifying the physical hardware changes and undocumented silicon in an off-the-shelf smart plug.

#4 about 3 min

Automating physical exploit execution and firmware extraction

The agent plans the engagement and acquires an encrypted flash dump from the bootloader.

#5 about 2 min

Intercepting local communications via cloned access points

Attempts to monitor device activity using a rogue AP and man-in-the-middle strategies.

#6 about 3 min

Analyzing BLE attack surfaces for vulnerabilities

Enumerating unauthenticated BLE services and gathering fingerprint data from the device radio.

#7 about 2 min

App layer defenses and TLS certificate pinning

How the companion app successfully prevented network interception by enforcing strict certificate checks.

#8 about 6 min

Bypassing physical enclosures for UART flash decryption

Desoldering uncooperative casing to access debug pads and retrieve plain text AES keys.

#9 about 2 min

Refining the agent by automating physical hardware restarts

Upgrading test environments with persistent power control tools to eliminate human intervention loops.

#10 about 2 min

Assessing the collapse of obscurity as a defense

Why traditional limitations of time and specialized knowledge no longer stop automated vulnerability discovery.

#11 about 2 min

Releasing isolated capabilities and persistent data risks

The implications of open-sourcing tool integrations while keeping the AI reasoning engines local.

#12 about 3 min

Addressing questions on model guardrails and alternative entry techniques

Audience questions cover LLM security bypasses and alternative chip-off data extraction methods.

Matching moments

3:38 min

Evaluating security risks in autonomous artificial intelligence agents

Chris Heilmann Chris Heilmann +2 · LIVE

2:18 min

Managing security risks introduced by autonomous AI agents

Christian Heilmann Christian Heilmann · World Congress 2025

2:04 min

The shift from credential abuse to software exploitation

Christian Heilmann Christian Heilmann +1 · World Congress 2026 North America

6:25 min

Coding hazards and software supply chain vulnerabilities

Isaac Evans Isaac Evans · World Congress 2026 North America

2:25 min

Understanding the lethal trifecta of AI agent compromise

Abdel Fane Abdel Fane · World Congress 2026 North America

11:34 min

Rapid prototyping with AI agents at hackathons

Chris Heilmann Chris Heilmann +2 · LIVE

Upcoming sessions on this topic

Open session

Beware of Strangers Bearing Code: Open Source Trust in the Agent Era

  • Vikram Vaswani

    Consultant

Open session

Autopsy of an Autonomous Incident: When the Agent Made It Worse

  • Navin Pai

    StackGen

    Director of Engineering

Open session

Architecting Trusted AI: Coupling Multi-Agent Systems with dbt Semantic Store for Zero-Hallucination

  • Pushkar Mishra

    J.P. Morgan

    Senior Vice President

Open session

Supply Chain Security for the Everyday Engineer

  • Pradumna Saraf

    Kestra Technologies

    Quality Assurance Engineer

Open session

ULTRON: Your Agent Has No Hands - Real-Time Voice, MCP, and Ten Phones on Stage

  • Sagar Tamang

    Two Spoon Technologies

    AI Engineer

Open session

Beyond File Dumps: Context Engineering for Coding Agents

  • Animesh Dutta

    Arm

    Senior Software Engineer