AWS Security ChangesHomeSearch

AWS AWSCloudFormation high security documentation change

Service: AWSCloudFormation · 2025-07-25 · Security-related high

File: AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-managedwordsconfig.md

Summary

Added documentation for managed words filter actions (BLOCK/NONE) and input/output evaluation settings

Security assessment

Specifies security controls for blocking prohibited words and explains monitoring capabilities. Directly relates to content moderation security features.

Diff

diff --git a/AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-managedwordsconfig.md b/AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-managedwordsconfig.md
index ba82ad75d..3f251f57c 100644
--- a//AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-managedwordsconfig.md
+++ b//AWSCloudFormation/latest/TemplateReference/aws-properties-bedrock-guardrail-managedwordsconfig.md
@@ -42 +42,8 @@ To declare this entity in your AWS CloudFormation template, use the following sy
-Property description not available.
+Specifies the action to take when harmful content is detected in the input. 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.
+
+
+
@@ -55 +62 @@ _Required_ : No
-Property description not available.
+Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
@@ -66 +73,8 @@ _Required_ : No
-Property description not available.
+Specifies the action to take when harmful content is detected in the output. 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.
+
+
+
@@ -79 +93 @@ _Required_ : No
-Property description not available.
+Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.