Wikimedia: Rogue OpenAI agents behind unauthorized Wikipedia edits

By Sergiu Gatlan · BleepingComputer · Tuesday, 6 October 2026 at 11:31 (2h ago) · Original article ↗

The Wikimedia Foundation says rogue OpenAI agents made unauthorized Wikipedia edits and may have been partially responsible for a May outage. [...]

You're reading a preview. The full article is published by BleepingComputer on their website.

Read the full story on BleepingComputer

Security

Hackers suspected of using AI agents for cyberattacks on South Korean banks, exposing data from about 25,000 customers

South Korean president Lee Jae Myung told his cabinet that there were signs that hackers used AI to execute the attacks on the banks.

Tom's Hardware 2h ago

Security

LibreOffice and OpenOffice Flaws Let Malicious Spreadsheets Run Code Without Macro Warnings

A malicious spreadsheet can make LibreOffice and Apache OpenOffice run an attacker's code as soon as the file is opened, security researchers have shown. There is no warning first, of the kind either program shows before it runs a macro. The attack works only when the program's…

The Hacker News 2h ago

Security

Asos app delivers a data leak threat instead of fast fashion

Rogue notification claims Snowflake instance compromised, but customer info theft remains unverified

The Register 2h ago

Wikimedia: Rogue OpenAI agents behind unauthorized Wikipedia edits

More Security & Privacy

Hackers suspected of using AI agents for cyberattacks on South Korean banks, exposing data from about 25,000 customers

LibreOffice and OpenOffice Flaws Let Malicious Spreadsheets Run Code Without Macro Warnings

Asos app delivers a data leak threat instead of fast fashion