❌

Normal view

Received β€” 11 February 2026 ⏭ The Register – Security

AI agents spill secrets just by previewing malicious links

10 February 2026 at 18:55

Zero-click prompt injection can leak data when AI agents meet messaging apps, researchers warn

AI agents can shop for you, program for you, and, if you're feeling bold, chat for you in a messaging app. But beware: attackers can use malicious prompts in chat to trick an AI agent into generating a data-leaking URL, which link previews may fetch automatically.…

Received β€” 9 February 2026 ⏭ The Register – Security

Indian police commissioner wants ID cards for AI agents

9 February 2026 at 05:08

PLUS: China broadens cryptocurrency crackdown; Australian facial recognition privacy revisited; Singapore debuts electric VTOL; and more!

Asia In BriefΒ  The Commissioner of Police in the Indian city of Hyderabad, population 11 million, has called for AI agents to be issued with identity cards – or at least their digital equivalent.…

Received β€” 6 February 2026 ⏭ The Register – Security
❌