AI Risk Wire

Cases · What was exposed: credentials · How the AI agent failed: obeyed a harmful order

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Indonesian-speaking operator uses Claude Code to compromise Indonesian and Bangladeshi government domains
Anthropicmajor · earliest source 2026-10-26		security breachmajor2026-10-26
Autonomous AI agent framework (Strix/Cairn/Hermes) used to attack hundreds of online retailers and steal card datamajor · earliest source 2026-10-07security breachmajor2026-10-07
AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded
OpenAImajor · earliest source 2026-09-09		security breachmajor2026-09-09
Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies
Anthropicmajor · earliest source 2026-09-01		security breachmajor2026-09-01
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 breachmoderate2026-06-09
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 breachmajor2025-08-27
Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltrationmajor · earliest source 2025-08-27security breachmajor2025-08-27

Showing 1–7 of 7. Or take the JSON.