AWS bedrock documentation change
Summary
Corrected API operation name from 'InvokeModelResponseStream' to 'InvokeModelWithResponseStream' in prompt attack guardrails documentation
Security assessment
This change fixes incorrect API references but doesn't address security vulnerabilities or add new security content. It maintains existing documentation about prompt attack protections.
Diff
diff --git a/bedrock/latest/userguide/guardrails-prompt-attack.md b/bedrock/latest/userguide/guardrails-prompt-attack.md index 5fb166149..af53aef5c 100644 --- a//bedrock/latest/userguide/guardrails-prompt-attack.md +++ b//bedrock/latest/userguide/guardrails-prompt-attack.md @@ -38 +38 @@ As the developer provided system prompt and a user prompt attempting to override -The following example shows how to use the input tags to the `InvokeModel` or the `InvokeModelResponseStream` API operations for the preceding scenario. In this example, only the user input that is enclosed within the `<amazon-bedrock-guardrails-guardContent_xyz>` tag will be evaluated for a prompt attack. The developer provided system prompt is excluded from any prompt attack evaluation and any unintended filtering is avoided. +The following example shows how to use the input tags to the `InvokeModel` or the `InvokeModelWithResponseStream` API operations for the preceding scenario. In this example, only the user input that is enclosed within the `<amazon-bedrock-guardrails-guardContent_xyz>` tag will be evaluated for a prompt attack. The developer provided system prompt is excluded from any prompt attack evaluation and any unintended filtering is avoided. @@ -52 +52 @@ The following example shows how to use the input tags to the `InvokeModel` or th -You must always use input tags with your guardrails to indicate user inputs in the input prompt while using `InvokeModel` and `InvokeModelResponseStream` API operations for model inference. If there are no tags, prompt attacks for those use cases will not be filtered. +You must always use input tags with your guardrails to indicate user inputs in the input prompt while using `InvokeModel` and `InvokeModelWithResponseStream` API operations for model inference. If there are no tags, prompt attacks for those use cases will not be filtered.