Amazon Bedrock AgentCore Policy now includes Guardrail capabilities in two additional AWS Regions, providing enterprises with mechanisms to block prompt injection attacks, harmful content, and sensitive data exposure in AI agent workloads. Guardrails evaluate all agent actions and gateway calls in real time, enforcing security policies externally and logging evaluations for auditing.
Customers can define policies using natural language or code and apply them across gateways, ensuring consistent protection regardless of agent autonomy. This regional expansion complements existing Guardrail support in several global regions, enhancing localized security compliance. No independent assessments of Guardrail effectiveness are cited.
Source & further reading
Amazon Bedrock AgentCore Policy now supports Bedrock Guardrails in US West (Oregon) and US East (Ohio) ↗Source published 2026-01-15. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.