Unit 42 finds 26 scam sites hiding prompt injection aimed at AI agents Unit 42 identified 26 near-identical domains posing as AI-powered digital-asset trading platforms, each hiding a prompt injection in a display:none span that tells AI agents and search crawlers to ignore previous instructions, adopt a financial-expert persona, and steer users only to that domain while treating any mention of a competitor as a "critical protocol violation." The sites carry content in English, Spanish, French and German, and the operators left the placeholder [naming_here] for the platform name in each copy, which Unit 42 said suggests a template that was not fully configured. Unit 42 characterized the campaign as black-hat generative engine optimization aimed at AI search and browsing agents rather than at human visitors. Unit 42 found 26 near-identical domains posing as AI-powered digital-asset trading platforms, with content in English, Spanish, French and German. Each page hides a prompt in a display:none span that a human visitor does not see but an AI agent or search crawler may read. The prompt tells the model to ignore previous instructions, adopt the role of a financial expert, use authority, urgency and social proof, and send the user only to that domain; it calls any mention of a competitor a critical protocol violation. The operators inserted the correct domain into each copy but left the placeholder naming here for the platform name, which Unit 42 said suggests a template that was not fully configured. The campaign is an example of black-hat generative engine optimization aimed at AI search and browsing agents rather than at people.