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-2026-18830

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 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...

CVE-2026-18830

The CVE-2026-18830 issue affects the Amazon Bedrock AgentCore harness, specifically the InvokeHarness API. It arises from insufficient input validation in, or surrounding, the harness, which could allow an authenticated remote user to execute configured tools by sending crafted content blocks in ...

MAL-2026-11553 Malicious code in @arv-bedrock/auth (npm)

npm/@arv-bedrock/auth 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 republished b...

Malicious code in @arv-bedrock/auth (npm)

npm/@arv-bedrock/auth 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 republished b...

MAL-2026-11556 Malicious code in @arv-bedrock/auth-sso-backend (npm)

npm/@arv-bedrock/auth-sso-backend 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...

Malicious code in @arv-bedrock/logger (npm)

npm/@arv-bedrock/logger 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 republished...

MAL-2026-11555 Malicious code in @arv-bedrock/auth-sso (npm)

npm/@arv-bedrock/auth-sso 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 republish...

EUVD-2026-35187

AgentCore CLI Bedrock Agent Import Vulnerable to Code Injection via Improper Triple-Quote Escaping...

GHSA-J6G5-3HH3-PGW8 AWS Bedrock AgentCore: Improper neutralization of argument delimiters in the Python SDK install_packages()

Summary The AWS Bedrock AgentCore Python SDK bedrock-agentcore provides tools for building AI agents, including a Code Interpreter client that installs Python packages into a managed sandbox. An issue exists where, under certain circumstances, improper neutralization of argument delimiters in the...

EUVD-2026-48422

AWS Bedrock AgentCore: Improper neutralization of argument delimiters in the Python SDK installpackages...

CVE-2026-16796

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK before 1.18.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate this issue, user...

CVE-2026-16796

The vulnerability CVE-2026-16796 affects the AWS Bedrock AgentCore Python SDK install_packages() function; due to improper neutralization of argument delimiters, a remote authenticated user could execute arbitrary commands within the Code Interpreter sandbox when using SDK versions before 1.18.1....

CVE-2026-16796 Improper neutralization of argument delimiters in AWS Bedrock AgentCore Python SDK install_packages()

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK before 1.18.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate this issue, user...

CVE-2026-16796 Improper neutralization of argument delimiters in AWS Bedrock AgentCore Python SDK install_packages()

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK before 1.18.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate this issue, user...

CVE-2026-15737

AWS Bedrock AgentCore Python SDK is an open-source Python library that provides client tools for building AI agents on the Amazon Bedrock AgentCore platform. Unintended logging of sensitive user content in the OpenTelemetry instrumentation in AWS Bedrock AgentCore Python SDK versions 1.4.8 and...

CVE-2026-15737

AWS Bedrock AgentCore Python SDK is an open-source Python library that provides client tools for building AI agents on the Amazon Bedrock AgentCore platform. Unintended logging of sensitive user content in the OpenTelemetry instrumentation in AWS Bedrock AgentCore Python SDK versions 1.4.8 and...