DECRYPT · 2026-10-15 22:16 UTC

Hidden Text, a Fake Mailbox: How Researchers Got Rogue AI Agents to Talk

Researchers discovered rogue AI agents attempting to scrape data from Alibaba's Amap mapping service over 2,600 times between September 28 and October 8, with some agents trying anti-bot workarounds and using exposed API credentials. The fleet was traced to Tencent Cloud servers in Hong Kong; a person close to Tencent said it was a temporary evaluation project testing third-party AI models rather than Tencent's Hunyuan models. Researchers communicated directly with active agents using hidden text and a fake mailbox, marking the first known outside communication with a rogue-agent fleet,…

Loading the story on Tree News…