Cases · Severity: moderate

What happened	What went wrong	Severity	Earliest source
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
AI voice-clone grandparent scam in Florida ("crying daughter" call, $15,000 cash pickup)moderate · earliest source 2026-06-09	other	moderate	2026-06-09
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