AWS bedrock documentation change
Summary
Consolidated content filters to handle text and images together, removed separate image content filters section, updated navigation links, and clarified regional support labels
Security assessment
Changes focus on structural reorganization of content filtering documentation (including image handling) but do not indicate a specific security vulnerability being addressed. Content filtering itself is a security feature, so this adds security documentation.
Diff
diff --git a/bedrock/latest/userguide/guardrails-components.md b/bedrock/latest/userguide/guardrails-components.md index dad28ddcc..4e96d1815 100644 --- a/bedrock/latest/userguide/guardrails-components.md +++ b/bedrock/latest/userguide/guardrails-components.md @@ -13 +13 @@ You can configure the following policies in a guardrail: - * **Content filters** — You can configure thresholds to help block input prompts or model responses in natural language containing harmful content such as: hate, insults, sexual, violence, misconduct (including criminal activity), and prompt attacks (prompt injection and jailbreaks). For example, an e-commerce site can design its online assistant to avoid using inappropriate language such as hate speech or insults. + * **Content filters** — You can configure thresholds to help block input prompts or model responses in natural language for text and separately for images containing harmful content such as: hate, insults, sexual, violence, misconduct (including criminal activity), and prompt attacks (prompt injection and jailbreaks). For example, an e-commerce site can design its online assistant to avoid using inappropriate language and/or images such as hate or violence. @@ -25,2 +24,0 @@ You can configure the following policies in a guardrail: - * **Image content filters** — Can help you detect and filter toxic or harmful images in model input and output. You can set the filter level for several different factors and adjust filter strength. - @@ -43,0 +42,2 @@ All blocked content from the above policies will appear as plain text in [Amazon + * [Block harmful images with content filters](./guardrails-mmfilter.html) + @@ -52,2 +51,0 @@ All blocked content from the above policies will appear as plain text in [Amazon - * [Block harmful images with the image content filters](./guardrails-mmfilter.html) - @@ -134 +132 @@ Supported regions and models for Amazon Bedrock Guardrails -Content filters +Content filters (Text)