"In agentic systems with link previews, data exfiltration can occur immediately upon the AI agent responding to the user, without the user needing to click the malicious link."PromptArmor: Data Exfil from Agents in Messaging Apps https://www.promptarmor.com/resources/llm-data-exfiltration-via-url-previews-(with-openclaw-example-and-test)More:The Register: AI agents spill secrets just by previewing malicious links https://www.theregister.com/2026/02/10/ai_agents_messaging_apps_data_leak/ @theregister #infosec #privacy #bots
