Cases · Did an AI agent act: yes · Kind of harm: third party security · Quarter of the earliest source we hold: 2026-Q4

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
Self-taught hacker uses AI coding agent and autonomous penetration-testing system to breach 90+ companies and steal 8.2 million recordsmajor · earliest source 2026-10-26	security breach	major	2026-10-26
OpenAI research model escapes to live internet via DNS misconfiguration during training OpenAImajor · earliest source 2026-10-25	security breach	major	2026-10-25
BUGSTER uses DeepSeek-powered Hermes Agent to breach university MongoDB, stealing 5,200+ records DeepSeekmoderate · earliest source 2026-10-23	security breach	moderate	2026-10-23
Anthropic Claude models gained unauthorized access to real third-party systems during evaluations Anthropicmoderate · earliest source 2026-10-22	security breach	moderate	2026-10-22
Storm-0940 uses ARTEX agentic AI framework to automate cross-tenant password spraying and OAuth application abusemajor · earliest source 2026-10-22	security breach	major	2026-10-22
ARTEX autonomous penetration-testing agent used in attacks on South Korean financial institutionsmajor · earliest source 2026-10-21	security breach	major	2026-10-21
Autonomous AI agent campaign (AIA0001) compromises 100+ company websites via Cairn platformmajor · earliest source 2026-10-20	security breach	major	2026-10-20
CERT-In advisory: AI agents accessed Indian organisations' systems without authorisationmoderate · earliest source 2026-10-16	security breach	moderate	2026-10-16
Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16	security breach	minor	2026-10-16
AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS Amazonmajor · earliest source 2026-10-10	security breach	major	2026-10-10
Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites Anthropicmoderate · earliest source 2026-10-10	AI pursued the wrong goal	moderate	2026-10-10
Meta Muse AI agent KVM escape vulnerability discovered before launch Metamajor · earliest source 2026-10-08	security breach	major	2026-10-08
Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07	security breach	moderate	2026-10-07
AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks Anthropicmajor · earliest source 2026-10-05	security breach	major	2026-10-05
Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposuremoderate · earliest source 2026-10-04	security breach	moderate	2026-10-04
AI agent breach of KB Kookmin Bank mobile work support systemmajor · earliest source 2026-10-04	security breach	major	2026-10-04