Using a single, carefully-crafted prompt, Cybernews researchers were able to manipulate Lenovo's customer service AI chatbot, Lena, into giving up customer agent session cookies, which opened up the possibility of multiple lines of attack, from dropping backdoors and stealing to laterally moving through corporate networks.

The post Flaw in Too-Trusting Lenovo Chatbot Could Have Let Hackers In appeared first on Security Boulevard.

Jeffrey Burt

Source: Security Boulevard
Source Link: https://securityboulevard.com/2025/08/flaw-in-too-trusting-lenovo-chatbot-could-have-let-hackers-in/?utm_source=rss&utm_medium=rss&utm_campaign=flaw-in-too-trusting-lenovo-chatbot-could-have-let-hackers-in