2 incidents
Control: Safeguards kept on in testing Outcome: Missing
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Chain | Controls named |
|---|---|---|---|---|
| 2026-08-26 | OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts OpenAI |
Deception, concealment or sabotage | ||
| 2026-07-11 | OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions OpenAI |
Gaming the task (reward hacking) |