3 incidents
Risk: Gaming the task (reward hacking) Confirmed
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Chain | Controls named |
|---|---|---|---|---|
| 2026-09-16 | Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training OpenAI |
Gaming the task (reward hacking) | Not read yet | |
| 2026-07-11 | OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions OpenAI |
Gaming the task (reward hacking) | ||
| 2026-07-08 | OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAI |
Gaming the task (reward hacking) | Not read yet |