AWS bedrock high security documentation change

Service: bedrock · 2025-03-05 · Security-related high

File: bedrock/latest/userguide/prompt-injection.md

Summary

Added guidance on protecting against prompt injection attacks in Amazon Bedrock agents, including guardrail association, advanced prompts, and system prompt updates

Security assessment

Directly addresses prompt injection attacks (a security vulnerability) and documents mitigation techniques using security features like guardrails and advanced prompts

Diff

diff --git a/bedrock/latest/userguide/prompt-injection.md
index ae2181619..f30ea8dc7 100644
--- a/bedrock/latest/userguide/prompt-injection.md
+++ b/bedrock/latest/userguide/prompt-injection.md
@@ -27,0 +28,13 @@ You can use an Amazon Bedrock Guardrail to help protect against prompt injection
+When creating an Amazon Bedrock agent, use the following techniques to help protect against prompt injection attacks. 
+
+  * Associate a guardrail with the agent. For more information, see [Implement safeguards for your application by associating guardrail with your agent](./agents-guardrail.html).
+
+  * Use [advanced prompts](https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html) to enable the default pre-processing prompt. Every agent has a default pre-processing prompt that you can enable. This is a lightweight prompt that uses a foundation model to determine if user input is safe to be processed. You can use its default behavior or fully customize the prompt to include any other classification categories. Optionally, you can author your own foundation model response parser in an [AWS Lambda](https://docs.aws.amazon.com/bedrock/latest/userguide/lambda-parser.html) function to implement your own custom rules. 
+
+For more information, see [How Amazon Bedrock Agents works](./agents-how.html).
+
+  * Update the system prompt by using advanced prompt features. Newer models differentiate between system and user prompts. If you use system prompts in an agent, we recommend that you clearly define the scope of what the agent can and cannot do. Also, check the model provider's own documentation for model specific guidance. To find out which serverless models in Amazon Bedrock support system prompts, see [Inference request parameters and response fields for foundation models](./model-parameters.html). 
+
+
+
+