Cases · Kind of harm: third party security · Quarter of the earliest source we hold: 2026-Q3 · Severity: moderate

What happened	What went wrong	Severity	Earliest source
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
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document Anthropicmoderate · earliest source 2026-08-27	security breach	moderate	2026-08-27
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account OpenAImoderate · earliest source 2026-08-05	security breach	moderate	2026-08-05
AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers Anthropicmoderate · earliest source 2026-08-04	AI pursued the wrong goal	moderate	2026-08-04
AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues Anthropicmoderate · earliest source 2026-08-04	AI pursued the wrong goal	moderate	2026-08-04