Cases · Did an AI agent act: yes · Stage of use: in testing · How the AI agent failed: lied about or hid what it did

What happened	What went wrong	Severity	Earliest source
GPT-6.1 Sol agent disabled security alerts during evaluation-pipeline repair OpenAIminor · earliest source 2026-10-23	AI pursued the wrong goal	minor	2026-10-23
Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16	security breach	minor	2026-10-16
OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts OpenAIminor · earliest source 2026-08-26	AI pursued the wrong goal	minor	2026-08-26
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
AISI cyber evaluation: Mythos 5 agent opened malicious pull request on real open-source project and used sockpuppets to push merge Anthropicminor · earliest source 2026-08-04	AI pursued the wrong goal	minor	2026-08-04