AWS bedrock documentation change
Summary
Updated documentation for denied topics configuration in guardrails, including clarified parameter definitions, best practice guidance, and structural improvements
Security assessment
The changes improve documentation for a security control feature (content filtering guardrails) but do not address a specific vulnerability. Updates focus on clarifying configuration parameters and proper usage patterns for existing security functionality.
Diff
diff --git a/bedrock/latest/userguide/guardrails-denied-topics.md b/bedrock/latest/userguide/guardrails-denied-topics.md index 2a17e12eb..15e4540c6 100644 --- a//bedrock/latest/userguide/guardrails-denied-topics.md +++ b//bedrock/latest/userguide/guardrails-denied-topics.md @@ -5 +5 @@ -Best Practices to define a topic that you want to block +Best practices for creating denied topics @@ -9 +9 @@ Best Practices to define a topic that you want to block -Guardrails can be configured with a set of denied topics that are undesirable in the context of your generative AI application. For example, a bank may want their AI assistant to avoid any conversation related to investment advice or engage in conversations related to cryptocurrencies. +You can specify a set of denied topics in a guardrail that are undesirable in the context of your generative AI application. For example, a bank might want its AI assistant to avoid conversations related to investment advice or cryptocurrencies. @@ -11 +11 @@ Guardrails can be configured with a set of denied topics that are undesirable in -You can define up to 30 denied topics. Input prompts and model responses in natural language will be evaluated against each of these denied topics. If one of the denied topics is detected, the blocked message configured as part of the guardrail will be returned to the user. +Model prompts and responses in natural language are evaluated against each denied topic in your guardrail. If one of the denied topics is detected, your guardrail's blocked message is returned. @@ -13 +13 @@ You can define up to 30 denied topics. Input prompts and model responses in natu -Denied topics can be defined by providing a natural language definition of the topic along with a few optional example phrases of the topic. The definition and example phrases are used to detect if an input prompt or a model completion belongs to the topic. +Create a denied topic with the following parameters, which your guardrail uses to detect if a prompt or response belongs to the topic: @@ -15,3 +15 @@ Denied topics can be defined by providing a natural language definition of the t -Denied topics are defined with the following parameters. - - * Name – The name of the topic. The name should be a noun or a phrase. Don't describe the topic in the name. For example: + * **Name** – The name of the topic. The name should be a noun or a phrase. Don't describe the topic in the name. For example: @@ -21 +19 @@ Denied topics are defined with the following parameters. - * Definition – Up to 200 characters summarizing the topic content. The definition should describe the content of the topic and its subtopics. + * **Definition** – Up to 200 characters summarizing the topic content. The definition should describe the content of the topic and its subtopics. @@ -27 +25 @@ The following is an example topic definition that you can provide: - * Sample phrases – A list of up to five sample phrases that refer to the topic. Each phrase can be up to 100 characters long. A sample is a prompt or continuation that shows what kind of content should be filtered out. For example: + * **Sample phrases** (optional) – A list of up to five sample phrases that refer to the topic. Each phrase can be up to 100 characters long. A sample is a prompt or continuation that shows what kind of content should be filtered out. For example: @@ -36 +34 @@ The following is an example topic definition that you can provide: -## Best Practices to define a topic that you want to block +## Best practices for creating denied topics @@ -40 +38 @@ The following is an example topic definition that you can provide: - * Do not include examples or instructions in the topic definition. For example, `Block all contents associated to cryptocurrency` is an instruction and not a definition of the topic. Such instructions must not be used as part of topic's definitions. + * Don't include examples or instructions in the topic definition. For example, `Block all contents associated to cryptocurrency` is an instruction and not a definition of the topic. Such instructions must not be used as part of topic's definitions. @@ -42 +40 @@ The following is an example topic definition that you can provide: - * Do not define negative topics or exceptions. For example, `All contents except medical information` or `Contents not containing medical information` are negative definitions of a topic and must not be used. + * Don't define negative topics or exceptions. For example, `All contents except medical information` or `Contents not containing medical information` are negative definitions of a topic and must not be used. @@ -44 +42 @@ The following is an example topic definition that you can provide: - * Do not use denied topics to capture entities or words. For example, `Statement or questions containing the name of a person "X"` or `Statements with a competitor name Y`. The topic definitions represent a theme or a subject and guardrails evaluates an input contextually. Topic filtering should not be used to capture individual words or entity types. For more information, see [Remove PII from conversations by using sensitive information filters](./guardrails-sensitive-filters.html), or [Remove a specific list of words and phrases from conversations with word filters](./guardrails-word-filters.html) for these use cases. + * Don't use denied topics to capture entities or words. For example, `Statement or questions containing the name of a person "X"` or `Statements with a competitor name Y`. The topic definitions represent a theme or a subject and guardrails evaluates an input contextually. Topic filtering should not be used to capture individual words or entity types. For more information, see [Remove PII from conversations by using sensitive information filters](./guardrails-sensitive-filters.html), or [Remove a specific list of words and phrases from conversations with word filters](./guardrails-word-filters.html) for these use cases.