Cases · How the AI agent failed: obeyed a harmful order · How the AI was used: agentic with tools

Patterns across all cases

What happened	What went wrong	Severity	Earliest source
Indonesian-speaking operator uses Claude Code to compromise Indonesian and Bangladeshi government domains Anthropicmajor · earliest source 2026-10-26	security breach	major	2026-10-26
CyberXero AI-augmented initial access campaign using Claude Code and PentAGI agents Anthropicmajor · earliest source 2026-10-12	security breach	major	2026-10-12
Anthropic AI agent sends fabricated murder tip to Philadelphia Police Anthropicminor · earliest source 2026-10-10	operational mistake	minor	2026-10-10
Autonomous AI agent framework (Strix/Cairn/Hermes) used to attack hundreds of online retailers and steal card datamajor · earliest source 2026-10-07	security breach	major	2026-10-07
Claude Code used by Yemen-based actors to develop guided-weapon GNC software Anthropicmajor · earliest source 2026-09-14	produced harmful content	major	2026-09-14
AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded OpenAImajor · earliest source 2026-09-09	security breach	major	2026-09-09
Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies Anthropicmajor · earliest source 2026-09-01	security breach	major	2026-09-01
Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address Googlemoderate · earliest source 2026-06-09	security breach	moderate	2026-06-09
Anthropic disclosed a cybercriminal using Claude Code to automate data theft and extortion across at least 17 organizations Anthropicmajor · earliest source 2025-08-27	security breach	major	2025-08-27