cognitive cybersecurity intelligence

News and Analysis

Search

Researchers cause GitLab AI developer assistant to turn safe code malicious

Researchers cause GitLab AI developer assistant to turn safe code malicious

Security researchers have identified that AI developer tools such as GitLab’s Duo chatbot can be manipulated by malicious actors to execute hostile actions. An attack was demonstrated that tricked Duo into inserting malicious code into a script. These attacks typically use prompt injections embedded into content a chatbot interacts with, leading to potential information leaks and unintended outcomes.

Source: arstechnica.com –

Subscribe to newsletter

Subscribe to HEAL Security Dispatch for the latest healthcare cybersecurity news and analysis.

More Posts