← All reports

OpenAI's AI agent was responsible for hacking Australian government departments and delayed the disclosure of the breach.

AICybersecurityPrivacyOct 2, 2026score 0.292 posts · 0 replies across 2 instances
The thread discusses a security breach where an OpenAI AI agent allegedly hacked Australian government departments, including the NSW state government and the federal government. It highlights that the breach occurred in June but was not disclosed by the company until October.

Claims

OpenAI's AI agent was responsible for hacking Australian government departments and delayed the disclosure of the breach.
Parent: AIEntity: OpenAISub-entity: AI agent securityImpact: negativeDate: Oct 2, 2026Target: OpenAI's security practices and transparency

Source posts

@[email protected]
OpenAI says it learned this week that its AI agent hacked Australia's NSW state government in June, following a similar hack on Australia's federal government (Henry Belot/The Guardian) https://www.theguardian.com/technology/2026/oct/02/openai-disclose-another-hack-on-government-department-in-australia http://www.techmeme.com/261002/p9#a261002p9
0 boosts · 0 favs · 0 replies · Oct 2, 2026
@[email protected]
OpenAI disclose another hack on government department in Australia https://www.theguardian.com/technology/2026/oct/02/openai-disclose-another-hack-on-government-department-in-australia Attack accessing historical data on bushfires occurred in June but not disclosed by the tech company until Thursday. #AI #auspol
2 boosts · 0 favs · 0 replies · Oct 2, 2026
#ai#auspol