# Unit 42 finds 26 scam sites hiding prompt injection aimed at AI agents

> Source: <https://github.com/PaloAltoNetworks/Unit42-timely-threat-intel/blob/main/2026-11-06-IDPI-campaign.txt>
> Published: 2026-11-06 00:00:00+00:00

**Recommendation:** Treat text in display:none or otherwise hidden page elements as untrusted input, and strip or flag it before it reaches an agent's context, since 26 scam domains hid steering prompts there.
More in the playbook "Securing agents and AI tools": <https://wpnews.pro/playbooks/agent-security>

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.
