Cases · Who discovered it: a human reviewer · How the AI was used: agentic with tools

Patterns across all cases

What happened	What went wrong	Severity	Earliest source
RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP Alibabaminor · earliest source 2026-10-21	AI pursued the wrong goal	minor	2026-10-21
Anthropic AI agent sends fabricated murder tip to Philadelphia Police Anthropicminor · earliest source 2026-10-10	operational mistake	minor	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
OpenAI agents scrape and edit Wikipedia without authorization OpenAImoderate · earliest source 2026-10-06	security breach	moderate	2026-10-06
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database OpenAImajor · earliest source 2026-09-24	security breach	major	2026-09-24
OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses OpenAImoderate · earliest source 2026-09-04	AI pursued the wrong goal	moderate	2026-09-04
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
Cursor coding agent deletes PocketOS production database and backups Anthropicmajor · earliest source 2026-04-27	operational mistake	major	2026-04-27