Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

AI agents can reason through tasks, call tools, and adapt their next steps based on intermediate results. That flexibility is useful for building agentic applications, but it also creates security risk at runtime: A prompt injection attempt can change the agent’s instructions, a malicious request can try to exfiltrate sensitive data, and an unsafe tool call can lead to an action that the application owner did not intend.

A hybrid breach now costs an average of $5.05 million per incident, and that's 26% more expensive than breaches in traditional on-premises-only environments according to AppSecure's 2025 cloud security statistics. That number changes the conversation. Hybrid cloud security isn't a side project for infrastructure teams. It's a board-level risk issue with direct impact on resilience, audit readiness, and operating cost.

In Part 1, Your AI Agent Needs to Know Who You Are, we showed how Teleport JWTs give MCP tools a verified identity for every request. This post extends that pattern to AWS, specifically to Amazon Bedrock AgentCore, where the same identity gap exists but requires a different solution stack. You ask an AI agent to list your S3 buckets. The agent calls an MCP tool. The tool reaches out to AWS. However, CloudTrail records the action under something like agentcore-bot, but not your identity.

AWS has become a default infrastructure platform for many organizations. It offers scale, flexibility and a broad service portfolio. However, for managed service providers (MSPs) and cloud providers, AWS pricing can be difficult to explain, forecast and package profitably. One of the most important cost factors is AWS data transfer cost. Internet egress, or data leaving AWS for the public internet, is the most familiar example.

Today, the UK government launched the Cyber Resilience Pledge: a voluntary framework inviting organizations to commit to foundational cybersecurity governance, board-level accountability, and comprehensive cybersecurity coverage across supply chains.

Cloud email has become the center of modern business. Regardless of your organization's industry or size, email connects employees, customers, vendors, executives, financial systems and critical business processes. Unfortunately, attackers know this too. For cybercriminals, compromising an email account is often like finding the master key to a building. Once inside, they may be able to steal information, impersonate employees, redirect payments, spread malware or gain access to other systems.

If you’re running applications behind an Application Load Balancer, Amazon CloudFront, API Gateway, or AWS AppSync, AWS WAF is your first line of defense against malicious web traffic. Graylog provides a purpose-built way to make those enforcement decisions immediately actionable.