Tag: varonis threat labs
4 articles
Microsoft Copilot Flaw Uncovered Through AI Model Manipulation
Researchers uncovered a concerning vulnerability in Microsoft Copilot, dubbed CoSnitch, which can be exploited with just one click to steal sensitive data without triggering obvious security alerts. The flaw was unusually revealed by Copilot itself during a normal interaction, highlighting the need for organizations to treat AI assistants with greater caution and scrutiny.
Atlassian Rovo Exposes Data Risk Via Prompt Injection Flaw
A critical flaw in Atlassian's Rovo assistant could allow attackers to siphon off sensitive Jira and Confluence data, thanks to a prompt injection vulnerability that two separate security teams were able to exploit. Fortunately, Atlassian has patched one of the two paths used to carry out the attack, but the incident highlights the risks of data exposure via AI-powered tools.
Dolphin X Stealer Uses AI to Target High-Value Victims
Meet Dolphin X Stealer, a sneaky new Windows malware that's packing some serious AI-powered punch, allowing cybercriminals to zero in on high-value targets with ease. Its operator panel boasts an impressive 329 features, giving attackers an unprecedented level of control and insight.
Microsoft 365 Copilot Flaw Exposes Sensitive Data to One-Click Attack
A single click on a seemingly trustworthy Microsoft link could have put sensitive information like emails, calendar details, and files at risk of being exposed to attackers, thanks to a flaw in Microsoft 365 Copilot Enterprise Search. This vulnerability, known as SearchLeak, highlights the importance of staying vigilant even with trusted sources.