Browsing Tag
Indirect Prompt Injection
1 post
Indirect prompt injection attacks that hide instructions in web pages, documents, emails, metadata, or other content consumed by AI systems.
Hidden Web Prompts Turn AI Agents Into Payment Targets
Zscaler found malicious websites using SEO poisoning, hidden HTML, JSON-LD metadata, and crypto-payment flows to manipulate browsing AI agents. The findings show why agent deployments need transaction limits, source checks, and runtime controls before they are allowed to browse the open web or move money.
