Policy: AWS > Bedrock > Enforced Guardrail Configuration > Settings > Selective Content Guarding > System

How the enforced guardrail evaluates SYSTEM prompt content.

- COMPREHENSIVE (default, strictest) evaluates all system-prompt content regardless of caller tagging. - SELECTIVE evaluates only content explicitly tagged with <guard> markers by the caller.

Targets

This policy targets the following resource types:

AWS > Bedrock > Enforced Guardrail Configuration

Primary Policy

This policy is used with the following primary policy:

AWS > Bedrock > Enforced Guardrail Configuration > Settings > Selective Content Guarding

Controls

Setting this policy configures this control:

AWS > Bedrock > Enforced Guardrail Configuration > Settings

Policy Specification

Schema Type	`string`
Default	`COMPREHENSIVE`
Valid Values [YAML]	`COMPREHENSIVE` `SELECTIVE`

In Your Workspace

Policy Settings by Type report

Developers

Category URI

tmod:@turbot/turbot#/control/categories/security

Policy Type URI

tmod:@turbot/aws-bedrock#/policy/types/enforcedGuardrailConfigurationSettingsSelectiveContentGuardingSystem

GraphQL

query policyType(id: "tmod:@turbot/aws-bedrock#/policy/types/enforcedGuardrailConfigurationSettingsSelectiveContentGuardingSystem") { … }

query policySettings(filter: "policyTypeId:'tmod:@turbot/aws-bedrock#/policy/types/enforcedGuardrailConfigurationSettingsSelectiveContentGuardingSystem'") { … }

query policyValues(filter: "policyTypeId:'tmod:@turbot/aws-bedrock#/policy/types/enforcedGuardrailConfigurationSettingsSelectiveContentGuardingSystem'") { … }

CLI

Get Policy Type

turbot graphql policy-type --id "tmod:@turbot/aws-bedrock#/policy/types/enforcedGuardrailConfigurationSettingsSelectiveContentGuardingSystem"

Get Policy Settings

turbot graphql policy-settings --filter "policyTypeId:tmod:@turbot/aws-bedrock#/policy/types/enforcedGuardrailConfigurationSettingsSelectiveContentGuardingSystem"