ARTEX AI Open-Source Pentest Tool Misused in Breaches and LLMjacking Cloud Attacks
WorkOS confirmed a data breach in which an attacker used the open-source multi-agent penetration-testing framework ARTEX AI to access an internal sales application and steal customer communication summaries. Chinese hackers reportedly used the same framework in automated attacks on more than 200 organizations across 14 countries. A UK school estate was hit by a ransomware attack suspected, but not confirmed, to have been AI-assisted. Google has reported LLMjacking, where stolen cloud credentials or API keys are used to run costly AI models, has generated over $1 million in fraudulent charges, with some organizations losing more than $100,000 in a single day. Experts advise treating AI API keys with the same care as root cloud credentials and rotating them regularly.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.
Discussion (0)
Log in to join the discussion and vote.
Log in