AWS compares two access architectures for Bedrock AgentCore Runtime. The API Gateway pattern validates a user JWT, binds the client session identifier to the authenticated subject, and forwards the token through a proxy in an isolated VPC. A runtime resource policy and endpoint security group restrict the accepted network path. The AgentCore Gateway pattern instead uses OAuth client-credentials authorization and a runtime workload allowlist; a request interceptor forwards verified user identity because the outbound machine token replaces the user's token. Both samples add per-user session limits, per-session invocation limits and authorization logging. This distinction matters: a valid token alone does not establish session ownership or prove that a request passed through the intended gateway. The linked CDK examples are explicitly non-production samples. Their session binding and bypass tests are useful starting points, but downstream authorization and failure behavior still require deployment-specific validation.
AgentCore ingress: bind sessions to users and test gateway bypass
Related research
More curated notes connected through Agent Security and AI Engineering.
OWASP Top 10 for Agentic Applications for 2026
OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.
A five-step roadmap to closing the AI evaluation gap
The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.
FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project
OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.