Gen Agent Trust Hub

The skill generates sandbox security policies based on user input and API documentation. It includes features to automatically search for documentation for well-known services. The primary security risk is indirect prompt injection, as the skill fetches and processes external content from the web to generate security configurations. The skill implements various safety checks, such as policy validation and warnings for overly broad permissions, to mitigate risks.

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