cybrlab-ai/PreClickPreClick: An intent + security layer for agent browsing that verifies each destination before an agent proceeds, applying analyst-like reasoning, adaptive behavior, and continuous improvement. It enables AI agents and any MCP-compatible client to analyze URLs for malicious content and security threats before navigation. BASIC USAGE Agent: Hey, PreClick - I want to open this link to book a room. PreClick: ALLOW (low risk + destination matches intent). Agent: Hey, PreClick - I want to open this link to invest in crypto. PreClick: DENY (high risk and/or intent mismatch). Telco Agent: Hey, PreClick - validate this URL for the SMS campaign (intent: Device trade-in promo). PreClick: ALLOW (low risk + intent match).