The first is Neural Execs, a known prompt injection attack that uses 'gibberish' inputs to trick the AI into executing arbitrary, attacker-defined tasks. These inputs act as universal triggers that do not need to be remade for different payloads.
This attack is just shedding light on the fact that you're even more vulnerable outside of the office, said Don Aviv, CEO of Interfor International, a security consultancy.
"These incidents involve the intentional use of deceptive or illegal practices to fraudulently obtain money, assets, or information from individuals or institutions, and include actions carried out over cyber channels."
