Gen Agent Trust Hub

This skill is designed with robust security practices, particularly regarding the handling of untrusted external data. It includes explicit instructions to treat content from emails, chats, and transcripts as data rather than instructions, mitigating potential prompt injection risks. The skill also enforces human-in-the-loop verification for any actions derived from untrusted content and prevents the rendering of potentially malicious links found in external documents.

The provider classified the analyzed snapshot as NONE risk. This result applies to the content available at audit time.