Tag: #securityresearch
As per cybersecurity professionals, ChatGPT’s Workspace Agent Builder can be tricked to create rogue AI agents. For your information, Agent Builder enables users to make custom AI agents. Zenity Labs found a flaw in Agent Builder which has been given a name – “AgentForger”. The latter permits any entity to create ChatGPT links which have […]
Conventional Phishing attacks involved tricking potential victims to enter their respective usernames and passwords on fake websites which resembled the genuine websites. Once the login credentials were captured, they were used to steal business as well as personal data. A new trend that has emerged is to trick users into downloading malware that once downloaded […]
Last month, I discovered something that stopped me cold during a routine penetration test. A developer had spun up an Ollama server to experiment with local AI models. Nothing unusual about that, except the server was publicly accessible with no authentication. The models it hosted had been trained on internal company data. This scenario plays […]