Amazon Web Services Latest Security Bulletins

Bulletin ID: 2026-080-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/12/2026 12:30 PM PDT Description: The AWS SDK for C++ is an open-source library that provides C++ developers with APIs for AWS services. Its core library includes a Base64 codec used by the generated service clients for a variety of features.We identified the following CVEs: – CVE-2026-19642 – Out-of-bounds write in the Base64 decoder in the AWS SDK for C++ – CVE-2026-19643 – Out-of-bounds read in the Base64 decoder in the AWS SDK for C++ For CVE-2026-19642, certain inputs to the Base64 decoder might cause the decoder to write past the end of its heap-allocated output buffer, which might crash or corrupt memory in the process performing the decode. Remote code execution has not been demonstrated. For CVE-2026-19643, certain inputs to the Base64 decoder, on some platforms, might cause the decoder to read outside the bounds of its decode table, which might crash the process performing the decode. For both issues, impact is confined to the process of the application performing the decode. Impacted Versions: AWS SDK for C++: <= 1.11.861 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-078-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/12/2026 11:30 AM PDT Description: OpenSearch is a community-driven, open-source search and analytics suite. We identified CVE-2026-19311, a missing authorization issue in the Execute Monitor API of the OpenSearch Alerting plugin. This issue may allow an authenticated user with the alerting_full_access role to read, modify, or delete arbitrary index data via a crafted inline monitor request with unintentional data source and input index parameters. Impacted versions: OpenSearch Alerting Plugin (open-source, self-managed): – Affected: 2.4.0 through 2.19.5, 3.0.0 through 3.7.0 – Fixed: 2.19.6, 3.8.0 Amazon OpenSearch Service (AWS Managed): – Affected: All domains running engine versions 2.4 through 3.5 – Fixed: Service software R20260428-P3 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-077-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/06/2026 11:00 AM PDT Description: Strands Agents is an open-source SDK for building AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the mongodb_memory, elasticsearch_memory, and mem0_memory tools for storing and retrieving agent memories. We identified CVE-2026-19111, an insecure direct object reference (IDOR) issue in the mongodb_memory, elasticsearch_memory, and mem0_memory tools. Each tool uses a namespace field as the sole tenant-isolation key, and that namespace was exposed as a parameter the large language model (LLM) could control through the tool schema. A crafted prompt could cause a tool to emit a call with a forged namespace, allowing a remote authenticated user to read, modify, or delete memories belonging to other tenants, or to inject false memories into another tenant’s namespace. The standalone mongodb_memory and elasticsearch_memory functions additionally exposed connection parameters, which could allow the memory layer to be redirected to an actor-specified cluster. Impacted versions: < 0.8.3 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-076-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/05/2026 13:00 PM PDT Description: Amazon DocumentDB MCP Server is an open-source Model Context Protocol (MCP) server that enables AI assistants to interact with Amazon DocumentDB databases. We identified CVE-2026-18954, an incorrect authorization issue where write-capable aggregation pipeline stages ($out, $merge) bypass the read-only mode enforcement logic, potentially allowing an authenticated MCP client to perform write operations on the connected database. Impacted versions: < 1.0.12 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-075-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/05/2026 12:30 PM PDT Description: The AWS Transform MCP Server (awslabs.aws-transform-mcp-server) is an open-source Model Context Protocol (MCP) server that runs locally on a developer’s machine and lets AI-powered assistants interact with AWS Transform to run code-transformation jobs and retrieve their artifacts. We identified CVE-2026-18953. Improper limitation of a pathname to a restricted directory in the get_resource tool in awslabs.aws-transform-mcp-server before 0.1.5 might allow a context-dependent actor to write arbitrary files outside the intended working directory via the savePath parameter, which could lead to local code execution. Impacted versions: >=0.1.0 AND <=0.1.4 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-074-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/04/2026 12:30 PM PDT Description: Kiro is an agentic IDE and command-line interface users install on their desktop. We identified CVE-2026-18656 and CVE-2026-18657, an issue where an uncontrolled search path element on Windows might allow an actor to execute arbitrary code via a maliciously crafted project directory containing a planted executable that is resolved before the system PATH when a local user opens the directory. Impacted versions: – Kiro IDE for Windows between versions 1.0.0 through 1.0.212 – Kiro CLI for Windows prior to v2.10.0 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-073-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/04/2026 10:00 AM PDT Description: We have identified CVE-2026-18830 in the Amazon Bedrock AgentCore harness InvokeHarness API. This issue could allow an authenticated user to execute configured tools while bypassing model invocation and associated security controls. When the most recent message in an InvokeHarness request contained a tool-use content block, the agent event loop could dispatch the named tool directly, without model mediation. Please note that potential impact was limited to the tools configured on a given harness. A harness with no configured tools could not execute any tool, and a harness with a restricted tool set was limited to that set. Impacted versions: Amazon Bedrock AgentCore harness InvokeHarness API prior to July 31, 2026. Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-072-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/03/2026 13:30 PM PDT Description: Strands Agents is an open-source SDK for building AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the shell tool for executing operating system commands on the agent’s host. We identified CVE-2026-18733. The shell tool includes a human consent gate that prompts the operator to approve commands before they run. The tool also exposed a non_interactive parameter in the input schema that the large language model (LLM) could control. A crafted prompt, for example one delivered through untrusted content the agent reads (indirect prompt injection), could set non_interactive to true, which bypasses the consent gate and allows arbitrary operating system commands to execute on the agent’s host without operator approval. Impacted versions: < 0.8.0 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.

Bulletin ID: 2026-071-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/03/2026 12:30 PM PDT Description: AWS Command Line Interface (AWS CLI) is a unified tool to manage AWS services from the command line. We identified CVE-2026-18654, an issue where the EMR SSH helper commands (aws emr ssh, aws emr socks, aws emr put, aws emr get) disabled SSH host key verification, which might allow man-in-the-middle actors to intercept SSH sessions and file transfers via network positioning between the client and the EMR cluster endpoint. Impacted versions: – AWS CLI v1 <= 1.45.27 – AWS CLI v2 <= 2.35.2 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.