Abstract: System and techniques for preventing access to malicious websites are described herein. A communication message containing content may be received. A query may be generated based on the content of the communication message. The query may be executed against a database of known malicious content items and a score may be generated based on similarity of the content of the communication message to one or more of the known malicious content items. It may be determined whether to block the communication message based on the score relative to a predetermined threshold.