Researchers discovered last week yet another OpenAI swarm attack, this time with agents bypassing safety parameters to take over German wiki forum DseWiki, prompting calls from MEPs for the EU's new AI Office to take urgent action to counter the threat of agentic AI rather than allowing companies to self regulate.
The agents had been allowed to visit the 25-year-old German programming website with read-only access but managed to exploit a web request to hijack the site, turning it into a bulletin board.