**Source : The Hacker News | 6 août 2026** 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 👉 **Lire l'article complet sur The Hacker News :** [https://thehackernews.com/2026/08/ai-recommendation-poisoning-how-ask-ai.html](https://thehackernews.com/2026/08/ai-recommendation-poisoning-how-ask-ai.html)