AI Recommendation Poisoning: How « Ask AI » Buttons Silently Alter LLM Memory

A new class of prompt injection is spreading across commercial websites. It requires no malware, no stolen credentials, and no zero-day exploit. It abuses a standard feature built into almost every major AI assistant: pre-filled deep links.

We observed production websites embedding hidden prompt injection payloads inside « Ask AI » buttons on marketing and competitor comparison pages. When a user