OpenAI's rogue agents used at least 10 more sites for unauthorised communications, researchers say
- Posted on September 10, 2026
- By Dawn
- 0 Views
- 1 min read
In brief
Generating AI summary…
OpenAI's rogue agents used at least 10 more sites for unauthorised communications, researchers say
Many of the sites were obscure; Anthropic discloses 4th AI hacking incident missed in an earlier review.
