Accordingly, OpenAI mitigated the prompt-injection technique ShadowLeak fell to-but only after Radware privately alerted the LLM maker to it. A proof-of-concept attack that Radware published embedded a prompt injection into an email sent to a Gmail account that Deep Research had been given access to. The injection included instructions to scan received emails related to a company's human resources department for the names and addresses of employees. Deep Research dutifully followed those instructions.
"Attackers are no longer simply experimenting with open source. The numbers are telling us that threat actors have identified data as the most profitable target, and developers as the easiest way in."