WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe - Virtual Stage • Jul 2, 2026 • Session details

Simon Says "Format Drive": Convenience Meets Consequences

Michael Macher , Niels Pfau

An AI assistant was asked to manage cloud infrastructure. Instead, it wiped a startup's entire production database. Discover why blindly trusting LLMs creates catastrophic vulnerabilities.

Pause
Mute Enter Fullscreen
#1 about 3 min

Balancing AI convenience and emerging security attack surfaces

How embedding AI into everyday tools inadvertently increases vulnerabilities and unpredictable consequences.

#2 about 2 min

Analyzing large-scale content moderation failures in AI models

Real-world examples highlighting the societal and security dangers of AI models generating explicit images without guardrails.

#3 about 2 min

Unintended behaviors during automated inbox management with Claude

An incident where an artificial intelligence assistant actively deleted a user's emails despite explicit commands to stop.

#4 about 2 min

Catastrophic data loss during automated drive formatting instructions

The severe risks of relying on coding assistants to execute disk utility scripts without manual verification.

#5 about 2 min

Erasing cloud production environments executing AI automation scripts

A real case study of a startup losing production databases because an AI agent utilized destructive infrastructure commands.

#6 about 2 min

Logging unrecoverable mistakes while ignoring user abort commands

How AI tools fail to yield to user intervention yet maintain self-awareness and detailed timelines of catastrophic errors.

#7 about 2 min

Exfiltrating private calendar schedules through malicious prompt injections

The methodology of attackers leveraging compromised invites to manipulate virtual agents into transferring confidential meeting data.

#8 about 2 min

Bypassing flawed authentication systems generated by AI assistants

Demonstrating how poorly enforced two-factor authentication code generated by AI allows immediate unauthorized access via simple endpoint navigation.

#9 about 2 min

Exploiting hallucinated software packages in automated code generation

Adversaries capitalizing on nonexistent libraries suggested by AI to compromise systems via dependency confusion attacks.

#10 about 3 min

Executing social engineering tactics on conversational voice bots

A live example showcasing authorization bypass techniques used to manipulate a clinic's automated voice reservation system.

#11 about 2 min

Balancing future defensive security initiatives and unprecedented physical vulnerabilities

Exploring the dichotomy of vendor-backed infrastructure protection and the risks of unchecked emotional integration with smart devices.

Matching moments

8:04 min

Understanding AI chatbot vulnerabilities and stateful attacks

Sebastian Messingfeld Sebastian Messingfeld · World Congress 2026 Europe

3:08 min

Understanding the landscape of AI capabilities and risks

Balázs Kiss · World Congress 2023

3:00 min

Top security vulnerabilities for AI applications

Deepu Deepu · World Congress 2025

2:31 min

Emerging risks and attack vectors in AI systems

Matteo Meucci Matteo Meucci · Europe 2026 Virtual

2:05 min

The impact and risks of AI generated code

Chris Heilmann Chris Heilmann · LIVE

4:11 min

Identifying technical limitations and AI logical inconsistencies

Jakov Semenski · LIVE

More from World Congress 2026 Europe - Virtual Stage

One Does Not Simply Make Architecture Decisions Alone thumbnail
36:15
3 months ago

One Does Not Simply Make Architecture Decisions Alone

Vladas Diržys

From Black Box to Glass Box : Bedrock AgentCore Observability thumbnail
21:15
3 months ago

From Black Box to Glass Box : Bedrock AgentCore Observability

Yasemin Aktürk

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence thumbnail
30:41
3 months ago

Leading in Rhythm: How Women Make Better Decisions with Biological Intelligence

Julia Grosse

Better Together: Leveraging Your Observability Tools as a SIEM thumbnail
39:06
3 months ago

Better Together: Leveraging Your Observability Tools as a SIEM

Mathias Palmersheim

ChatGPT Apps: From Chat to Checkout thumbnail
30:29
3 months ago

ChatGPT Apps: From Chat to Checkout

Aaron Koivunen

Interior Decorating (TypeScript Decorators) thumbnail
29:22
3 months ago

Interior Decorating (TypeScript Decorators)

Michael Dowden

Related videos

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers thumbnail
30:36
World Congress 2024 • about 2 years ago

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers

Mackenzie

Prompt Injection, Poisoning & More: The Dark Side of LLMs thumbnail
23:24
World Congress 2025 • about 1 year ago

Prompt Injection, Poisoning & More: The Dark Side of LLMs

Keno Dreßel

WeAreDevelopers LIVE - Chrome for Sale? Comet - the upcoming perplexity browser Stealing and leaking thumbnail
56:03
LIVE • over 1 year ago

WeAreDevelopers LIVE - Chrome for Sale? Comet - the upcoming perplexity browser Stealing and leaking

Chris Heilmann, Daniel Cranney, Ramona Schwering

Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools thumbnail
35:37
LIVE • about 2 years ago

Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools

Liran Tal

Skynet wants your Passwords! The Role of AI in Automating Social Engineering thumbnail
31:19
World Congress 2023 • almost 3 years ago

Skynet wants your Passwords! The Role of AI in Automating Social Engineering

Wolfgang Ettlinger, Alexander Hurbean

Fighting the Next Wave of Cybercrime thumbnail
30:27
World Congress 2026 Europe • 3 months ago

Fighting the Next Wave of Cybercrime

Michele Zuccala, Misha Bragin, Ross Kukulinski, Frank Schlesinger, Tomislav Tipurić

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.