AWS bedrock-agentcore documentation change
Summary
Added Topics section with navigation links and updated apostrophe formatting
Security assessment
The main change adds a navigation section (Topics) with links to related documentation pages. The apostrophe change is typographical. While the documentation is about security policies, this change doesn't add new security documentation or address specific security issues - it improves document structure and navigation. The security implications of the policy enforcement boundary description remain unchanged.
Diff
diff --git a/bedrock-agentcore/latest/devguide/policy.md b/bedrock-agentcore/latest/devguide/policy.md index 5bdfb5645..6c480d9e1 100644 --- a//bedrock-agentcore/latest/devguide/policy.md +++ b//bedrock-agentcore/latest/devguide/policy.md @@ -16,0 +17,29 @@ Policy in AgentCore supports fine-grained permissions based on user identity and +###### Topics + + * Key benefits + + * Key features + + * [Getting started with Policy in AgentCore](./policy-getting-started.html) + + * [Core concepts](./policy-core-concepts.html) + + * [AgentCore Gateway and Policy in AgentCore IAM Permissions](./policy-permissions.html) + + * [Create a policy engine](./policy-create-engine.html) + + * [Create a policy](./policy-create-policies.html) + + * [Writing policies in natural language](./policy-natural-language.html) + + * [Validate and test policies](./policy-validate-policies.html) + + * [Use policies](./policy-use-policies.html) + + * [Example policies](./example-policies.html) + + * [Advanced features and topics for Policy in AgentCore](./policy-advanced.html) + + + + @@ -29 +58 @@ Define what actions an agent is allowed to perform - including which tools it ca -Every agent action through Amazon Bedrock AgentCore Gateway is intercepted and evaluated at the boundary outside of agent's code - ensuring consistent, deterministic enforcement that remains reliable regardless of how the agent is implemented. +Every agent action through Amazon Bedrock AgentCore Gateway is intercepted and evaluated at the boundary outside of agent’s code - ensuring consistent, deterministic enforcement that remains reliable regardless of how the agent is implemented.