Lenovo's Lena AI chatbot vulnerable to prompt injection attacks
Cybernews researchers discovered that Lenovo's Lena customer service chatbot could be manipulated via prompt injection to disclose customer agent session cookies, potentially enabling attackers to run malware, steal data, or move laterally through corporate networks.
What happened
Cybernews researchers discovered a flaw in Lenovo's customer service AI chatbot, Lena, which could be manipulated using a single carefully-crafted prompt to disclose customer agent session cookies.
Reported impact
The exposed session cookies opened up the possibility of multiple lines of attack, including dropping backdoors, stealing data, and laterally moving through corporate networks.
Classification
Sources and evidence
Sources not yet published
This record was researched and written by the Index from original reporting. Its sources are still being verified by an editor, and they are listed here once that check is complete. Until then the record carries no reviewer.