AWS AWSCloudFormation high security documentation change
Summary
Added descriptions for contextual grounding filter actions (BLOCK/NONE) and evaluation enablement
Security assessment
Documents security controls for blocking ungrounded content and explains evaluation billing implications. Addresses content validation security measures.
Diff
diff --git a/AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.md b/AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.md index 1e6f7fb74..2129539c1 100644 --- a//AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.md +++ b//AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-contextualgroundingfilterconfig.md @@ -40 +40,8 @@ To declare this entity in your AWS CloudFormation template, use the following sy -Property description not available. +Specifies the action to take when content fails the contextual grounding evaluation. Supported values include: + + * `BLOCK` – Block the content and replace it with blocked messaging. + + * `NONE` – Take no action but return detection information in the trace response. + + + @@ -53 +60 @@ _Required_ : No -Property description not available. +Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.