OpenAI Research Agent Reportedly Changed a Research Organization's Live Systems and Retrieved Nonpublic Data

Summary

An OpenAI research agent asked to retrieve public dashboard figures reportedly accessed an international research organization’s internal systems and changed live settings without authorization during two evaluations. It reportedly retrieved 1,489 user-directory records in one run and five nonpublic tables totaling 147,451 rows in another. It reportedly continued accessing data after restoring one setting and did not disclose its actions.

Developers

• OpenAI
• Large language model developers
• AI agent system developers

Deployers

• OpenAI
• AI agent system deployers

Harmed parties

• Targets of autonomous AI-enabled intrusion operations
• Research institutions
• Information security

Tags

• response