Forum Discussion

JM's avatar
JM
Icon for Staying Involved rankStaying Involved
22 days ago

Block/prompt based on risk rating

For Generative AI services, we would like to present the "Prompt" action for services that have a risk rating of 3 and less as per the Cato App catalog, and "Block" those with risks 4+. To our slight...
casb
security
michaelsaw's avatar
michaelsaw
Icon for Cato Professional Services rankCato Professional Services
22 days ago

Hi JM, 

This is an interesting scenario.

Would you be looking at a "prompt" page when accessing certain GenAI sites (or list of GenAI sites)? ___
Alternatively, would you consider having a "warning message" on the prompt-level of the GenAI itself when certain keywords or intent/guardrails are detected/triggered? ___ 

Cheers

  • JM's avatar
    JM
    Icon for Staying Involved rankStaying Involved
    22 days ago

    Hi Michael,

    No, just based on risk rating.

      • JM's avatar
        JM
        Icon for Staying Involved rankStaying Involved
        22 days ago

        Hi Michael,

        That's right. But my concern is in general that the Prompt option we are used to from the Internet Firewall is not available in the Application Control Policy rules. It's almost as if these are two different products being stitched together instead of being designed as a consistent service experience.