AWS bedrock documentation change
Summary
Updated console instructions for editing guardrails, including cross-Region inference configuration, tag management, and policy modification steps
Security assessment
The changes clarify security-related configurations including cross-Region data handling and content filtering policies, but do not indicate remediation of a specific vulnerability. The addition of cross-Region inference configuration documentation relates to data residency controls, which is a security feature.
Diff
diff --git a/bedrock/latest/userguide/guardrails-edit.md b/bedrock/latest/userguide/guardrails-edit.md index 881f3e7e4..a2fedbfc6 100644 --- a//bedrock/latest/userguide/guardrails-edit.md +++ b//bedrock/latest/userguide/guardrails-edit.md @@ -7 +7 @@ -You can edit your guardrails by following these steps for the AWS Console or API: +You can edit your guardrails by following these steps for the Amazon Bedrock console or API: @@ -18 +18 @@ Console - 3. To the name, description, tags, or model encryption settings for the guardrail. Select **Edit** in the **Guardrail overview** section. + 3. To modify your guardrail's name, description, cross-Region inference configuration, or model encryption settings, select **Edit** in the **Guardrail Overview** section. When you're done, select **Save and exit**. @@ -20 +20 @@ Console - 4. To edit specific configurations for the guardrail, select **Working draft** in the **Working draft** section. + 4. To edit your guardrail's tags, select **Manage tags**. When you're done, select **Save and exit**. @@ -22 +22 @@ Console - 5. Select **Edit** for the sections containing the settings that you want to change. Make any edits that are needed to the messaging for denied prompts or responses. + 5. To modify what policies your guardrail uses, select **Working Draft** and then **Edit** for each type of policy that you want to configure. When you're done making changes to your guardrail's policies, select **Save and exit**. @@ -24,5 +24 @@ Console - 6. To edit filters for harmful categories, select **Configure harmful categories filter**. Select **Text** and/or **Image** to filter text or image content from prompts or responses to the model. Select **None, Low, Medium, or High** for the level of filtration you want to apply to each category. You can choose to have different filter levels for prompts or responses. You can select the filter for **prompt attacks** in the harmful categories. Configure how strict you want each filter to be for prompts that the user provides to the model. - - 7. Select **Edit** for any sections containing the settings that you want to change. - - 8. Select **Save and exit** to implement the edits on your guardrail. + 6. When you're done making changes to your guardrail, select **Save and exit**.