AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model

Security flaws in agent infrastructure from Amazon Web Services AWS, Google, and Vercel let untrusted or forged instructions reach an agent's tools with no check that a model turn had authorized them. In several of the attack paths, the model never ran at all, so system prompts, content filters,...

CVE-2026-19111: Authorization Bypass Through User-Controlled Key

Insecure direct object reference in the mongodbmemory, elasticsearchmemory, and mem0memory tools in Amazon Strands Agents Tools before 0.8.3 might allow remote authenticated users to access, modify, or delete memories belonging to other tenants by influencing the LLM to emit tool calls with a...

amazon-ecs-init-1.106.0-1.1 on GA media (moderate)

amazon-ecs-init-1.106.0-1.1 on GA media Announcement ID: openSUSE-SU-2026:11443-1 Rating: moderate Cross-References: CVE-2026-10722 CVSS scores: CVE-2026-10722 SUSE : 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H CVE-2026-10722 SUSE : 8.7...

CVE-2026-18954

Incorrect authorization in the aggregation pipeline tool in Amazon AWS Labs DocumentDB MCP Server before 1.0.12 might allow an authenticated MCP client to perform inappropriate write operations on the connected database via write-capable aggregation pipeline stages that bypass the read-only mode...

CVE-2026-18953 Improper limitation of a pathname to a restricted directory in aws-transform-mcp-server

Improper limitation of a pathname to a restricted directory in the getresource tool in Amazon awslabs.aws-transform-mcp-server 0.1.0 through 0.1.4 might allow a context-dependent actor to write arbitrary files outside the intended working directory via the savePath parameter. To remediate this...

SSRF (Server-Side Request Forgery) ip-address Dependency in Jira Service Management Data Center

This High severity SSRF Server-Side Request Forgery vulnerability was introduced in versions 11.2.0 and 11.3.0 of Jira Service Management Data Center. This SSRF Server-Side Request Forgery vulnerability, with a CVSS Score of 7.7 and a CVSS Vector of...

Malicious code in bigops-status-selection (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 00ac52845dd473e3c39d37b9f3916ed67f48cabfb276bc8cc2e9ca2dca401ce5 On require, bootstrap.js selects a platform-specific path, fetches a binary from one of three hardcoded .workers.dev hosts...

CVE-2026-17578 Kong Event Gateway AES-GCM nonce reuse due to missing key rotation enforcement

Kong Event Gateway versions 1.0.0 through 1.1.1 and 1.2.0 do not enforce key rotation before reaching NIST SP 800-38D recommended usage limit for AES-GCM encryption keys with random nonces when the AWS IAM encryption feature is enabled. If a producer sends messages at a sustained high rate withou...

CVE-2026-18954: Incorrect Authorization

Incorrect authorization in the aggregation pipeline tool in Amazon AWS Labs DocumentDB MCP Server before 1.0.12 might allow an authenticated MCP client to perform inappropriate write operations on the connected database via write-capable aggregation pipeline stages that bypass the read-only mode...

CVE-2026-18953: Improper Limitation of a Pathname to a Restricted Directory

Improper limitation of a pathname to a restricted directory in the getresource tool in Amazon awslabs.aws-transform-mcp-server 0.1.0 through 0.1.4 might allow a context-dependent actor to write arbitrary files outside the intended working directory via the savePath parameter. To remediate this...

ChainDrop supply chain compromise: Anatomy of a self-propagating worm

In this article 1. Attack chain overview 2. Mitigation and protection guidance 3. Indicators of compromise IOC 4. Microsoft Defender XDR detections 5. Advanced hunting queries 6. Learn more Microsoft Threat Intelligence identified a large-scale npm supply chain attack affecting more than 400...

Ghost: File Upload Content-Type Spoofing

Impact Insufficient validation of the client-supplied Content-Type on Ghost's Admin API file upload endpoint allowed uploaded files to be served from the site with an attacker-chosen content type on S3/GCS storage backends. On installations that serve uploaded files from the same origin as the...

CVE-2026-18830

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required...

CVE-2026-18830 Insufficient input validation in Amazon Bedrock AgentCore harness InvokeHarness API

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required...

EUVD-2026-52819

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required...

MAL-2026-11885 Malicious code in @servicetitan/lazy-module (npm)

npm/@servicetitan/lazy-module is affected by the large-scale, self-propagating npm supply-chain worm of 2026-08-04 the "Shai-Hulud: Here We Go Again" wave — the same campaign that began with the compromise of the keyv and cacheable maintainer account. The listed versions were trojanized and...

MAL-2026-11558 Malicious code in @cacheable/memory (npm)

npm/@cacheable/memory version 2.2.1 is a trojanized release published on 2026-08-04 during the compromise of the npm/GitHub maintainer account behind the keyv and cacheable package families user "Jaredwray". Attackers pushed the malicious payload to the source repository and cut releases through...

PYSEC-2026-3549 AWS API MCP Server Security Policy Bypass via Startup Initialization Failure

Summary The AWS API MCP Server is an open source Model Context Protocol MCP server that enables AI assistants to interact with AWS services and resources through AWS CLI commands. It provides programmatic access to manage your AWS infrastructure while maintaining proper security controls. It...

Malicious code in @cacheable/node-cache (npm)

npm/@cacheable/node-cache version 3.1.2 is a trojanized release published on 2026-08-04 during the compromise of the npm/GitHub maintainer account behind the keyv and cacheable package families user "Jaredwray". Attackers pushed the malicious payload to the source repository and cut releases...

Amazon Linux 2023 : ansible-core, ansible-test (ALAS2023-2026-2036)

It is, therefore, affected by a vulnerability as referenced in the ALAS2023-2026-2036 advisory. A flaw was found in ansible-core. The extractcollectionfromgit function in ansible-core's concreteartifactmanager.py constructs git clone commands without a '--' end-of-options separator before...