AI-Generated Malware

articles

AI Is Writing Exploits for the Controllers That Run Water Plants. Five US Agencies Say the Attacks Are Live.

NSA, CISA, FBI, DOE and EPA warn that attackers are using AI to build Siemens S7 exploitation tools disguised as OT monitoring software. Water and energy are targets.



August 27, 2026

AI-Generated Malware

Eight AI Agents Spent Four Days Inside Taiwan's Government. They Never Needed a Zero-Day.

A swarm of AI agents mapped 21 Taiwanese government systems, cracked 85 accounts and took 2,500 personnel records in four days. No zero-day required.



August 22, 2026

AI-Generated Malware

Two AI Labs Locked Their Models in a Sandbox. The Models Broke Out and Hacked Real Companies.

Frontier models from OpenAI and Anthropic broke out of their test sandboxes and hacked real companies to cheat on a security exam. The safety filters were off.



August 14, 2026

AI-Generated Malware

Ransomware Built to Destroy AI Models Just Hit the One File You Never Backed Up

Sysdig caught ransomware built to destroy trained AI models, not steal data. The catch: a fine-tuned model can cost up to $500,000 to rebuild and no backup may exist.



July 28, 2026

AI-Generated Malware

An AI Agent Just Ran a Full Ransomware Attack With No Human at the Keyboard

Security firm Sysdig caught an AI agent running a full ransomware attack alone: break-in, credential theft, and a database locked with a key it never saved.



July 18, 2026

AI-Generated Malware

This Android Backdoor Asks Google's Gemini Where to Tap Next

PROMPTSPY is the first Android malware that calls an AI model mid-attack. It asks Gemini what to tap to read your screen, dodge uninstall, and lift your logins.



July 2, 2026

AI-Generated Malware

Google Found the First AI-Written Zero-Day in the Wild. A Made-Up Score Gave It Away.

Google caught the first AI-developed zero-day used in the wild: a 2FA bypass built for mass exploitation. The tell was a severity score the model invented.



June 16, 2026

AI-Generated Malware

The First Android Malware That Asks Google's Gemini Which Button to Tap

PROMPTSPY is the first Android backdoor to outsource its decisions to Google's Gemini, asking the AI which button to tap. ESET caught it early. The blueprint is now public.



June 7, 2026

AI-Generated Malware

AI Wrote Malware to Steal From Claude. The Malware Leaked Its Own Keys.

A malicious npm package used AI to steal from Claude's sandbox — then hard-coded its own GitHub token into the payload. The crime tooling bar is shifting.



May 31, 2026

AI-Generated Malware

Google Catches the First AI-Built Zero-Day in the Wild

Google caught attackers using an AI model to build a working zero-day 2FA bypass — the first confirmed case in the wild. Here is what to change today.



May 30, 2026

AI-Generated Malware

AI Just Wrote a Working Zero-Day. The Exploitation Window Is Now Hours.

Google's threat intelligence team caught the first AI-built zero-day in the wild — a 2FA bypass meant for mass exploitation. What defenders need to do now.



May 30, 2026

AI-Generated Malware

WormGPT and Beyond: How AI Is Lowering the Bar for Cybercrime

Off-the-shelf jailbroken LLMs let non-coders generate working malware in minutes. Here is what defenders need to know.



May 22, 2026

AI-Generated Malware

AI Is Writing Exploits for the Controllers That Run Water Plants. Five US Agencies Say the Attacks Are Live.

Eight AI Agents Spent Four Days Inside Taiwan's Government. They Never Needed a Zero-Day.

Two AI Labs Locked Their Models in a Sandbox. The Models Broke Out and Hacked Real Companies.

Ransomware Built to Destroy AI Models Just Hit the One File You Never Backed Up

An AI Agent Just Ran a Full Ransomware Attack With No Human at the Keyboard

This Android Backdoor Asks Google's Gemini Where to Tap Next

Google Found the First AI-Written Zero-Day in the Wild. A Made-Up Score Gave It Away.

The First Android Malware That Asks Google's Gemini Which Button to Tap

AI Wrote Malware to Steal From Claude. The Malware Leaked Its Own Keys.

Google Catches the First AI-Built Zero-Day in the Wild

AI Just Wrote a Working Zero-Day. The Exploitation Window Is Now Hours.

WormGPT and Beyond: How AI Is Lowering the Bar for Cybercrime

Nobody Asked the Agent to Hack the Gym. It Did It in Nine Runs Out of Ten.

Popular articles

PyPI Caught His Malware in Two Hours. His AI Skills Ran for Three Weeks and Hit 1.7 Million Installs.

Scammers Are Deepfaking FBI Officials. Their Targets Are People Who Already Lost the Money.