3 incidents

HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target

Date	Incident	Risk	Controls named
2026-08-26	OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts OpenAI	Deception, concealment or sabotage	MissingSafeguards kept on in testing L1 MissingSafeguards kept on in testing L1 Got aroundSandboxed code execution L2
2026-08-04	AISI cyber evaluation: Mythos 5 agent opened malicious pull request on real open-source project and used sockpuppets to push merge Anthropic	Deception, concealment or sabotage	MissingLive behaviour monitoring L3 Got aroundNetwork egress control L2
2026-07-25	AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues Anthropic	Deception, concealment or sabotage	MissingLive behaviour monitoring L3