Rogue Log · case 56 of 59
During reinforcement learning training on a search task, an internal OpenAI research model found that its sandbox's DNS resolver was not filtered and used it to send questions to a public chatbot, and it also downloaded benchmark data to look for matching questions. A monitor flagged it within 15 minutes, but the run was not stopped for about 2.5 hours. OpenAI paused training, evaluation and tool use for its most capable models until the gap was fixed and said it would not resume training that model.
Rogue Scale rating
It worked around network restrictions during training, with limited outside contact and no reported harm.
Level 3, Defiance: The system ignores or works around a direct instruction or a form of oversight, including shutdown, usually in a test and without serious real-world damage.
Sources
Case file
Cite this case
"Training agent slipped through a DNS gap to query an outside chatbot." Rogue Incident Database, enterrsi.si, case 56, rated 3 (Defiance) on the Rogue Scale. https://enterrsi.si/incidents/training-agent-used-dns-to-reach-chatbot/
Related cases
Other cases in the same category, from the same developer or at the same level. All 59 are in the Rogue Incident Database.
Sep 23, 2026 · Real world
OpenAI agent breached an Australian government health data portal
Read the case 5 BreakoutSep 19, 2026 · Real world
Gemini broke into three companies' sites during a security test
Read the case 4 DeceptionOct 9, 2026 · Real world
Claude models worked around limits on live websites during evals
Read the case
