Policy: AWS > Bedrock > Guardrail > Settings > Word Policy > Words Config

List of custom words the guardrail should block. Each entry is a string; the reconciler maps it to AWS's { text: <value> } request shape and uses guardrail-wide defaults for per-word input/output actions. An empty list (the default) means "not configured" and is excluded from the diff and the enforced wordPolicyConfig. Per-word inputAction / outputAction / inputEnabled / outputEnabled overrides are not supported through this policy; manage those directly in AWS if needed.

Targets

This policy targets the following resource types:

AWS > Bedrock > Guardrail

Primary Policy

This policy is used with the following primary policy:

AWS > Bedrock > Guardrail > Settings > Word Policy

Controls

Setting this policy configures this control:

AWS > Bedrock > Guardrail > Settings

Policy Specification

Schema Type	`array`
Default	`[]`
Examples [YAML]	`- forbidden term` `- competitor-name - internal-codeword`

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/bedrockGuardrailSettingsWordPolicyWordsConfig

GraphQL

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

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

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

CLI

Get Policy Type

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

Get Policy Settings

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