4 article(s) in our index mention this organisation.
A research report by Adversa AI has revealed a significant security vulnerability in ten popular open-source AI coding agents, including GuardFall, which allows attackers to bypass safety checks and execute shell command…
A research report by Adversa AI has identified a significant security vulnerability in several popular open-source AI coding agents, dubbed ‘GuardFall’. This flaw stems from the agents’ reliance on Bash shell tricks, spe…
A recent analysis by Adversa AI tested and ranked 100 AI agents, revealing a concerning trend: nearly all agents possess a dangerous combination of excessive power, trust, and a lack of control – what they term the ‘leth…
A vulnerability, dubbed ChatGPhish, has been discovered in OpenAI’s ChatGPT that allows attackers to leverage the AI’s summarization feature to create phishing attacks. By appending malicious content to a webpage, attack…
