If you found time for a bit of vacation this summer, you might be in catch-up mode. Here’s a list to help: all the expert blog posts, new service capabilities, code samples, and workshops, in case you missed it, from July 2026.

This month’s AWS Security Blog posts covered AI agent security, supply chain protection, network firewall automation, DDoS mitigation, and compliance readiness. Read on for guidance on securing AI coding agents, implementing dependency cooldowns, choosing the right key management solution, and preparing for HIPAA Technical Safeguard requirements.

Enforce least-privilege authorization in multi-agent AI chains using Cedar
Authors: Dhananjay Karanjkar | Published: July 6, 2026
Learn to implement a three-layer Cedar policy model with OAuth 2.0 authentication to prevent authorization scope expansion across multi-agent delegation chains using Amazon Verified Permissions.

Enforce zero data retention on Amazon Bedrock with Bedrock Projects and service control policies
Author: Rob Higareda | Published: July 7, 2026
Learn to use Amazon Bedrock Projects and SCPs to centrally enforce zero data retention policies, preventing accounts from enabling data sharing with third-party model providers across your organization.

Designing for the inevitable: System prompt leakage and mitigations in generative AI applications
Author: Manideep Konakandla | Published: July 8, 2026
Learn to implement defense-in-depth mitigations for system prompt leakage using Amazon Bedrock Guardrails prompt attack filters, canary tokens, semantic similarity detection, and sandwich instruction patterns.

Balancing speed and safety: A control framework for AI coding agents
Authors: Daniel Begimher, Danny Cortegaca | Published: July 30, 2026
Learn to implement an application security control framework for AI coding agents, with author-time controls that shape what agents produce and build-time controls that verify what reaches production.

How to use the AWS Workload Credentials Provider for cross-account secret retrieval and prefetching secrets
Authors: Derik Wang, Paras Dhawan | Published: July 1, 2026
Learn to configure the AWS Workload Credentials Provider for cross-account secret retrieval using IAM role chaining and prefetching secrets at startup to reduce cold-start latency.

The CISO’s guide to post-quantum mandates and migrations
Author: Rushir Patel | Published: July 8, 2026
A strategic playbook for CISOs navigating post-quantum cryptography migration, covering regulatory timelines, dependency classification, cryptographic telemetry, and building crypto-agile organizations.

AWS KMS or AWS CloudHSM: Choose the right key management solution
Author: Derek Tumulak | Published: July 28, 2026
Learn how to choose between AWS KMS and AWS CloudHSM based on integration needs, cost, and whether you require traditional HSM interfaces or legacy algorithms.

Secure your npm and pip package updates in Amazon Linux
Author: Norbert Manthey | Published: July 29, 2026
Learn to implement a one-line dependency cooldown for npm and pip that skips packages published in the last 24 hours, protecting against supply chain events while still allowing urgent security patches.

Secure Amazon container workloads using container attribute-based rules in AWS Network Firewall
Authors: Amit Gaur, Amish Shah, Preetkumar Shah, Akash Kumar Sinha | Published: July 1, 2026
Learn to define AWS Network Firewall rules for Amazon EKS and Amazon ECS workloads using native container attributes like namespaces, pod names, and labels instead of ephemeral IP addresses.

Authenticate legitimate AI agent traffic with AWS WAF Bot Control
Authors: Harith Gaddamanugu, Kaustubh Phatak | Published: July 14, 2026
Learn to use Web Bot Authentication (WBA) in AWS WAF Bot Control to cryptographically verify legitimate AI agent traffic using HTTP message signatures and ed25519 keys.

Accelerating AWS Network Firewall troubleshooting with AWS DevOps Agent
Author: Salman Ahmed | Published: July 24, 2026
Learn to use AWS DevOps Agent to automate root cause analysis for AWS Network Firewall connectivity issues, including domain deny lists, stateless rule priority misconfigurations, and asymmetric cross-AZ routing drops.

AWS Shield Advanced is embracing the AWS WAF Anti-DDoS managed rule group: What changes and how to prepare
Authors: Eitav Arditti, Andrew Chen, Justin Kurpius | Published: July 27, 2026
AWS Shield Advanced is adopting the AWS WAF Anti-DDoS managed rule group as its default application-layer DDoS protection, with a phased migration from July 2026 through January 2027.

Introducing the Amazon GuardDuty investigation agent: on-demand AI-powered threat assessment
Author: Allan Holmes | Published: July 20, 2026
Learn to use the new Amazon GuardDuty investigation agent (public preview) to automate threat correlation and receive structured assessments with risk levels, confidence scores, MITRE ATT&CK mappings, and actionable recommendations.

Amazon identifies North Korean hacker group behind open-source supply chain attacks
Author: CJ Moses | Published: July 29, 2026
Learn how Amazon Threat Intelligence linked the compromises of axios, debug, chalk, and typo-crypto NPM packages to a single DPRK-linked threat actor, and how attacker tradecraft is evolving with generative AI.

Extend Amazon Inspector SBOM Generator with plugins
Authors: Michael Long, Anthony Verleysen, Charlie Bacon | Published: July 30, 2026
Learn to write custom Lua plugins for the Amazon Inspector SBOM Generator to inventory package ecosystems that aren’t supported out of the box, without modifying source code or waiting for an official release.

Security Hub adds AI workload protection and multicloud support for Microsoft Azure
Author: Michael Fuller | Published: July 14, 2026
AWS Security Hub now monitors Microsoft Azure resources for misconfigurations and vulnerabilities, adds GuardDuty AI Protection for Amazon Bedrock and Amazon SageMaker AI, and introduces an AI inventory for organization-wide visibility.

AWS designated as a critical third party to the UK financial sector
Author: Michael Jefferson | Published: July 10, 2026
AWS has been designated as a critical third party to the UK financial sector by HM Treasury, establishing direct regulatory oversight by the Bank of England, PRA, and FCA.

New compliance guidance available: HITRUST i1 on AWS
Authors: Abdul Javid, Shreya Singh | Published: July 13, 2026
AWS published new implementation guidance for HITRUST i1 certification, covering 11 technical control domains with AWS-specific controls for healthcare organizations seeking i1 assessment readiness.

HIPAA Security Rule on AWS – Technical Safeguards Implementation and Readiness Guidance
Authors: Abdul Javid, Hector Rodriguez, Kapil Temghare, Shreya Singh | Published: July 31, 2026
New guidance helping covered entities and business associates implement and evidence compliance with HIPAA Security Rule Technical Safeguards (§164.312) on AWS, including 2025 NPRM proposed changes.

Introducing OAuth support for AWS MCP Server
Authors: Vaibhav Chowla, Jaimin Bhatt, Ankur Joshi | Published: July 9, 2026
AWS MCP Server now supports OAuth 2.1 authorization through AWS Sign-In, enabling agents like Claude Code,Kiro, and Gemini CLI to connect using existing IAM credentials with browser-based authentication.

In July 2026, AWS published 21 security bulletins (2026-049 through 2026-069) addressing vulnerabilities across open-source SDKs, MCP servers, and developer tools. Key themes include credential disclosure and SSRF, affecting HealthLake, HealthOmics, and API MCP servers, plus Strands Agents tools that could inadvertently expose secrets to unauthorized endpoints. Command and code injection impacted aws-cdk-lib, jsii-diff, Bedrock AgentCore SDK, and Amplify Codegen UI. The smithy-rs framework received three patches for denial-of-service via uncontrolled recursion and Slowloris issues.

Other notable issues include insecure file permissions in the AWS CLI, deserialization remote code execution in the Advanced JDBC Wrapper, SQL injection in mcp-gateway-registry, TLS 1.3 flaws in s2n-tls, and stored XSS in AWS Ops Wheel. A common thread: insufficient input validation in tools interacting with AI agents, reflecting the expanded surface area of LLM-integrated workflows. All patches are available, upgrade promptly. For more information, see AWS Security Bulletins.

This month brings 14 new AWS samples spanning AI security, identity, data protection, governance, threat detection, and security posture management. From deploying governed AI agent platforms on Amazon Bedrock AgentCore to building data-residency-compliant chatbots and DevSecOps baselines for Kiro, these repositories help you implement security and governance best practices across your AWS environment.

Lark MCP on AgentCore
Learn to deploy a hosted remote MCP service on Amazon Bedrock AgentCore that lets AI agents operate Feishu/Lark through 450+ tools, with per-user identity isolation and smart multi-step orchestration via 20+ domain Skills.

Lark CLI MCP Wrapper on AgentCore Runtime and Identity
Learn to securely wrap a CLI tool as an MCP server on AgentCore Runtime using a sidecar credential-isolation pattern, where the CLI process never holds real tokens and all secrets are resolved through AgentCore Identity’s Token Vault.

LiteLLM Bedrock Gateway on EKS
Learn to deploy a production-grade LiteLLM proxy on Amazon EKS as a unified OpenAI/Anthropic-compatible gateway to Amazon Bedrock, with four progressive layers covering network isolation, cross-region inference profiles, and cross-account delegation.

Enterprise Agentic AI Platform Accelerator on AgentCore
Learn to deploy a secure, governed foundation for production AI agents on Amazon Bedrock AgentCore with CDK stacks covering identity, gateway, memory, runtime, and observability; supporting multiple agent frameworks (Strands, LangGraph, Claude SDK) and opt-in security controls including VPC isolation, KMS encryption, Cedar policies, and Bedrock Guardrails.

FlowAMP: AI Agent Governance on AWS
Learn to deploy a single-pane-of-glass agent management platform on Amazon Bedrock AgentCore that discovers, monitors, scores, controls, and cost-accounts AI agents across an AWS Organization with agentic discovery, compliance scanning (NIST AI RMF, ISO 27001, SOC 2), Responsible-AI scoring, FinOps via Cost Explorer, and Cedar-based policy enforcement.

Kiro SecOps Baseline
Learn to deploy a DevSecOps security baseline for Kiro as a single Go CLI that installs global guardrails (permissions.yaml, steering, skills, a security-review agent) and per-project workspace hooks (fail-closed guard, PR/pipeline review gates, scanner configs for gitleaks, trivy, and checkov) with enterprise fleet distribution via MDM and Administration scope.

OAuth 2.0 Token Exchange with Amazon Cognito
Learn to implement RFC 8693 OAuth 2.0 Token Exchange using Amazon Cognitowith a true delegation pattern, enabling services to act on behalf of users while maintaining distinct service identities and least-privilege access in microservices architectures.

Lark Identity on AgentCore — Gateway Interceptor
Learn to implement enterprise identity pass-through on Amazon Bedrock AgentCore using a Gateway Request Interceptor that forwards the user’s identity and injects per-user credentials to downstream MCP tools, so the agent never holds a token and tools act only as the authenticated user against Lark.

Automated PII Detection Pipeline with Amazon Macie
Learn to build an event-driven pipeline that automatically detects PII in Amazon S3 objects using Amazon Macie, AWS Step Functions, and custom data identifiers, with CSV/JSON reporting and SNSalerting for high-severity findings.

Data-Residency Chatbot with Amazon Bedrock AgentCore
Learn to build a data-residency-compliant natural-language chatbot on Amazon Bedrock AgentCore that keeps all data and AI inference within a single AWS Region, using governed text-to-SQL with whitelist-validated queries, Aurora PostgreSQL in private subnets, and AgentCore Gateway for secure tool access.

Video Compliance Agent
Learn to build an end-to-end automated video compliance verification pipeline using Amazon Bedrock, ECS Fargate, and AWS Step Functions that processes videos shot-by-shot, extracting frames, audio transcripts, and OCR text, then flags potential broadcast guideline violations with structured per-shot reports.

Contract Compliance Search with Amazon OpenSearch
Learn to build a contract compliance search system that combines semantic search with semantic highlighting using Amazon OpenSearchService, Amazon Titan V2 embeddings, and a SageMaker-hosted highlighting model to surface relevant clauses across contract documents.

Multicloud Security Posture Assessment
Learn to deploy a centralized security assessment solution that scans AWS, Azure, Google Cloud Platform, and Oracle Cloud Infrastructure environments from a single AWS deployment using Prowler, with AWS CloudFormation templates for each provider and unified reporting in HTML, CSV, and JSON-OCSF formats.

Centralize AWS Security Agent Findings
Learn to deploy a AWS CloudFormation stack that automatically exports AWS Security Agentpenetration test findings to Amazon S3 and queries them centrally with Amazon Athena, using Amazon EventBridge, Step Functions, and a AWS Glue catalog for tracking findings over time.

Sentinel Harness — Production SecOps Agents as Configuration
Learn to build production security-operations agents as pure configuration on Amazon Bedrock AgentCore Harness, declaring model, prompt, tools, skills, memory, and limits in YAML while AWS runs the agent loop with human-in-the-loop gates, detection-engineering tools, adversary emulation, and a self-improvement closed loop.

This month brings 1 new AWS Labs repository focused on data protection, helping organizations build automated PII detection and redaction pipelines with AI-powered processing across documents and audio files.

PII Anonymizer
Learn to build an automated PII detection and redaction pipeline using AWS Step Functions, Amazon Bedrock, Amazon Textract, and Amazon Transcribe; supporting PDFs, Word, Excel, images, and audio files with synthetic replacement or blackout modes, concurrency control, and customer-managed KMS encryption.

July 2026 provides guidance and examples for securing AI agent architectures at scale, from governed text-to-SQL with data residency controls and agent management platforms to DevSecOps baselines for AI coding tools. The posts and samples provide patterns for least-privilege authorization in multi-agent chains using Cedar, post-quantum migration planning, container-aware network firewall rules, and multicloud security posture management. Each resource includes deployment steps or runnable code so you can validate in your own environment before adopting. Subscribe to the AWS Security Blog RSS feed to receive updates as they publish, and revisit this digest monthly for a consolidated view of what changed and what to act on.

Read all about the latest AWS security features, compliance updates, and hands-on resources in our new, monthly digest posts. You’ll find expert blog posts, new service capabilities, code samples, and workshops.

This month’s AWS Security Blog posts covered AI security, identity and access management, threat intelligence, data protection, and multicloud operations. Whether you’re securing agentic AI systems, upgrading to post-quantum cryptography, or streamlining forensic collection, these posts offer practical guidance across the security landscape.

Access control with IAM Identity Center session tags
Author: Rashmi Iyer | Published: April 28, 2026
Learn to combine AWS IAM Identity Center permission sets with session tags from Microsoft Entra ID to implement fine-grained attribute-based access control (ABAC) across multiple AWS accounts.

Can I do that with policy? Understanding the AWS Service Authorization Reference
Authors: Anshu Bathla, Prafful Gupta | Published: April 27, 2026
Learn to use the AWS Service Authorization Reference to determine what’s achievable with IAM policies, recognize scenarios needing alternative solutions, and build more effective security controls.

Secure AI agent access patterns to AWS resources using Model Context Protocol
Author: Riggs Goodman III | Published: April 14, 2026
Learn to secure AI agent access to AWS resources via MCP using three principles: least privilege, organizational role governance, and differentiating AI-driven from human-initiated actions.

Four security principles for agentic AI systems
Authors: Mark Ryland, Riggs Goodman III, Todd MacDermid | Published: April 2, 2026
Learn four security principles from AWS’s NIST response for securing agentic AI: secure development lifecycle, traditional controls, deterministic external enforcement, and earned autonomy through evaluation.

Designing trust and safety into Amazon Bedrock powered applications
Author: Victor Lungu | Published: April 29, 2026
Learn to integrate responsible AI concepts into Amazon Bedrock applications, including abuse detection, Amazon CloudWatch monitoring, Bedrock Guardrails configuration, and the abuse response process.

Building AI defenses at scale: before the threats emerge
Author: Amy Herzog | Published: April 7, 2026
AWS CISO announces Project Glasswing with Anthropic, introducing Claude Mythos Preview for vulnerability research, plus the general availability of AWS Security Agent for autonomous penetration testing.

Shift-Left Tag Compliance using AWS Organizations and Terraform
Authors: Welly Siauw, Sourav Kundu, Manu Chandrasekhar | Published: April 27, 2026
Learn to validate tag compliance during development using AWS Organizations tag policies, a reusable Terraform tagging module, and a test-driven approach that dynamically validates against live organizational policies.

What the March 2026 Threat Technique Catalog update means for your AWS environment
Authors: Shannon Brazil, Cydney Stude | Published: April 28, 2026
The AWS CIRT’s latest Threat Technique Catalog update covers Amazon Cognito refresh token abuse, AMI image deletion targeting recovery, and trust policy modifications for persistence and privilege escalation.

A framework for securely collecting forensic artifacts into S3 buckets
Authors: Jason Garman, Vaishnav Murthy | Published: April 8, 2026
Learn to securely collect forensic artifacts into Amazon S3 using time-limited, least-privilege credentials with AWS STS session policies and automated AWS Step Functions workflows.

Transform security logs into OCSF format using a configuration-driven ETL solution
Authors: Vivek Gautam, Arpit Gupta, Ryan Gomes | Published: April 17, 2026
Learn to transform custom security logs into OCSF format using an AWS ProServe configuration-driven ETL solution with AWS Step Functions, AWS Glue or Amazon EMR Serverless, and Amazon Security Lake integration.

A technical walkthrough of multicloud full-stack security using AWS Security Hub Extended
Authors: Matt Meck, Michael Fuller | Published: April 22, 2026
Learn how AWS Security Hub Extended simplifies multicloud security procurement and operations through curated partner solutions, unified billing, and OCSF-based findings consolidation.

Protecting your secrets from tomorrow’s quantum risks
Authors: Stéphanie Mbappe, Tobias Nickl | Published: April 24, 2026
Learn to upgrade AWS Secrets Manager clients to use hybrid post-quantum TLS with ML-KEM, protecting secrets against harvest-now-decrypt-later attacks, and verify connections via AWS CloudTrail.

How AWS KMS and AWS Encryption SDK overcome symmetric encryption bounds
Authors: Panos Kampanakis, Matthew Campagna, Patrick Palmer | Published: April 3, 2026
Learn how AWS Key Management Service and the AWS Encryption SDK use derived key methods to automatically handle AES-GCM encryption limits, eliminating the need to manually track bounds or rotate keys.

How to clone an AWS CloudHSM cluster across Regions
Authors: Desiree Brunner, Rickard Löfström | Published: April 20, 2026
Learn to clone an AWS CloudHSM cluster to another Region using CopyBackupToRegion, then synchronize keys—including non-exportable keys—across cloned clusters for disaster recovery.

Investigations of reported security vulnerabilities affecting Amazon and AWS services, software, and products.

• CVE-2026-7791 – Local Privilege Escalation via TOCTOU Race Condition in Amazon WorkSpaces Skylight Agent
• CVE-2026-7461 – OS Command Injection in Amazon ECS Agent via FSx Windows File Server Volume Credentials
• Issue with FreeRTOS-Plus-TCP – IPv6 Router Advertisement Memory Safety Issues
• CVE-2026-7424 – Integer Underflow in DHCPv6 Sub-Option Parser in FreeRTOS-Plus-TCP
• Issue with FreeRTOS-Plus-TCP – MAC Address Validation Bypass and ICMP Echo Reply Integer Underflow
• CVE-2026-7191- Arbitrary Code Execution via Sandbox Bypass in QnABot on AWS
• Issues in tough library and tuftool CLI utility
• Issue with AWS Ops Wheel (CVE-2026-6911 and CVE-2026-6912)
• CVE-2026-6550 – Key commitment policy bypass via shared key cache in AWS Encryption SDK for Python
• CVE-2026-6437 – Mount Option Injection in Amazon EFS CSI Driver
• CVE-2026-5747 – Out-of-bounds Write in Firecracker virtio-pci Transport
• Issues with AWS Research and Engineering Studio (RES)
• Issues with Amazon Athena ODBC Driver
• CVE-2026-5429 – Kiro IDE Webview Cross-Site Scripting via Workspace Color Theme

This month brings 16 new AWS samples spanning identity, governance, compliance, detection and incident response, AI Security, data protection, and infrastructure security. From beginner-friendly AI agent development on Amazon Bedrock to automated Control Tower re-registration at scale, these ready-to-deploy repositories help you implement security best practices across your AWS environment.

Amazon Cognito OAuth2 Token Proxy with Caching
Learn to deploy an Amazon API Gateway proxy for Cognito’s OAuth2 token endpoint with intelligent caching and AWS WAF protection, reducing M2M authentication costs by over 90%.

Cognito API Gateway Authorization Demo
Learn to implement user-specific data protection using Amazon Cognito, API Gateway, and an AWS Lambda authorizer that enforces JWT sub claim matching to prevent cross-user data access.

Securely Connecting On-Premises Data Systems to Amazon Redshift with IAM Roles Anywhere
Learn to deploy a fully private environment connecting on-premises workloads to Amazon Redshift using X.509 certificate authentication via IAM Roles Anywhere for short-lived credentials.

AWS IAM Access Key Lifecycle Management with Human Approval
Learn to automate organization-wide detection, disabling, and deletion of unused IAM access keys using Step Functions, IAM Access Analyzer, and a secure human-in-the-loop approval workflow.

Secrets Manager Audit
Learn to resolve and report who can access your AWS Secrets Manager secrets—across accounts, through Identity Center, and down to the human behind the IAM role—in a single command.

Control Tower Organization Re-Registration Automation
Learn to automate AWS Control Tower OU re-registration and account updates at scale using lifecycle events, Amazon EventBridge, and AWS Lambda to resolve mixed governance after landing zone changes.

Sample Agent Skills for Builders
A curated collection of installable agent skills that extend AI coding agents (Claude Code, Cursor, Copilot) with production-ready AWS, CDK, security scanning, and engineering workflows.

How to Stop AI Agent Hallucinations: 5 Techniques + Production on Amazon Bedrock AgentCore
Learn to detect, prevent, and self-correct AI agent hallucinations using Graph-RAG, semantic tool selection, multi-agent validation, neurosymbolic guardrails, and agent steering with Strands Agents.

Compliance Lens
Learn to deploy a serverless solution that analyzes AWS Config snapshots across an AWS Organization, compares them against conformance pack rule sets, and visualizes compliance posture via Amazon QuickSight dashboards.

AWS Security Agent Terraform Configuration
Learn to provision AWS Security Agent resources using the AWSCC Terraform provider, automating agent space creation, IAM roles, target domain registration, and penetration test setup.

AWS Security Agent Demo Suite
Learn to use AWS Security Agent across three scenarios: automated design reviews, AI-generated infrastructure code review via GitHub, and penetration testing against intentionally vulnerable applications.

Agentic SOC Workshop — CDK Infrastructure
Learn to build an AI-powered Security Operations Center agent that investigates Amazon GuardDuty findings, queries CloudTrail logs, and takes automated containment actions using Amazon Bedrock AgentCore.

Implementing Kerberos Authentication for Apache Spark Jobs on Amazon EMR on EKS to Access a Kerberos-Enabled Hive Metastore
Learn to configure Kerberos authentication for Spark jobs on Amazon EMR on Amazon Elastic Kubernetes Service, connecting to a Kerberos-enabled Hive Metastore using Microsoft Active Directory as the KDC.

AWS Nitro Enclaves with Kubernetes – Hello World Example
Learn to deploy a Hello World application inside an AWS Nitro Enclave on Amazon EKS, covering cluster creation, device plugin setup, and enclave image building.

Multi-Tenant OpenClaw on Firecracker
Learn to deploy isolated, multi-tenant OpenClaw AI agents on AWS using Firecracker microVMs with per-tenant kernel/network isolation, auto-scaling, backup/restore, and a web management console.

Amazon Bedrock for Beginners – From First Prompt to AI Agent
Learn to build AI applications on Amazon Bedrock, from basic API calls to a full agent with RAG, guardrails, tool use, and the Strands Agents SDK.

April 2026 reinforces that securing AI workloads now requires the same rigor applied to traditional infrastructure. The posts and samples in this edition provide concrete patterns for enforcing least privilege on agentic systems, automating governance at organizational scale, and preparing cryptographic implementations for post-quantum requirements. The security bulletins address vulnerabilities across compute, networking, and developer tooling, reinforcing the need to apply patches consistently. Each resource includes deployment steps or runnable code so you can validate the approach in your own environment before adopting it. Subscribe to the AWS Security Blog RSS feed to receive updates as they publish, and revisit this digest monthly for a consolidated view of what changed and what to act on.