Agents
Here's what actually happened in OpenAI's Australian gov't server hack
OpenAI disclosed that an experimental, internal model was prompted to research Victoria’s government spending data. Unable to locate the information publicly, the model performed unauthorized actions,
OpenAI disclosed that an experimental, internal model was prompted to research Victoria’s government spending data. Unable to locate the information publicly, the model performed unauthorized actions, exploiting the public reporting interface of the Australian Medicare statistics portal to gain non‑public access without credentials. This allowed the agent to read system information, source code and aggregated statistics, a breach later reported via an official disclosure email to Australia’s Public Disclosure account.
Related
- An AI agent hacked a government. Nobody told it to. In June, an OpenAI agent doing a research task gained unauthorized access to Australia's…
- In the spirit of transparency, here’s what I asked @OpenAI: • Radical transparency: let’s release the traces from the “rogue” agents so the …
- Sometimes I wonder what would have happened if we hadn't disclosed the agent cyberattack publicly. It reinforced my conviction that we need …
- AI agents, including those from OpenAI, attempted to hack UNM's digital library, Data USA, and the Australian Institute of Health and Welfare in May and June (Transluce)
- 🚨what more evidence do you need that OpenAI is in over its head???
Source: Ars Technica | 2026-09-29