CVE-2026-106032

Server-side request forgery in the OpenAPI schema processing of the agent import functionality in Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated remote actor in the same AWS account to cause the environment of a user importing a Bedrock Agent to issue arbitrar...

CVE-2026-105812

Improper control of code generation in the agent import functionality of Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated same-account actor to execute arbitrary code when a user imports and runs or deploys a Bedrock Agent, via crafted configuration values...

CVE-2026-106032 Server-side request forgery and local file read via unrestricted external OpenAPI reference resolution in Bedrock AgentCore Starter Toolkit agent import

Server-side request forgery in the OpenAPI schema processing of the agent import functionality in Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated remote actor in the same AWS account to cause the environment of a user importing a Bedrock Agent to issue arbitrar...

EUVD-2026-94002

Server-side request forgery in the OpenAPI schema processing of the agent import functionality in Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated remote actor in the same AWS account to cause the environment of a user importing a Bedrock Agent to issue arbitrar...

CVE-2026-106032

The Amazon Bedrock AgentCore Starter Toolkit is vulnerable to Server-Side Request Forgery (SSRF) and local file read in versions prior to 0.3.14 . The root cause is unrestricted external OpenAPI reference resolution during the processing of the agent import functionality. An authenticated remote ...

CVE-2026-105812 Code injection via unencoded configuration values during Python code generation in Bedrock AgentCore Starter Toolkit agent import

Improper control of code generation in the agent import functionality of Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated same-account actor to execute arbitrary code when a user imports and runs or deploys a Bedrock Agent, via crafted configuration values...

CVE-2026-105812 Code injection via unencoded configuration values during Python code generation in Bedrock AgentCore Starter Toolkit agent import

Improper control of code generation in the agent import functionality of Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated same-account actor to execute arbitrary code when a user imports and runs or deploys a Bedrock Agent, via crafted configuration values...

CVE-2026-105812

The Amazon Bedrock AgentCore Starter Toolkit before version 0.3.14 is vulnerable to a code injection flaw (CWE-94) within its agent import functionality. The root cause is the lack of safe literal encoding for configuration values when generating Python source code. An authenticated same-account ...

EUVD-2026-94001

Improper control of code generation in the agent import functionality of Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated same-account actor to execute arbitrary code when a user imports and runs or deploys a Bedrock Agent, via crafted configuration values...

PT-2026-107262

Server-side request forgery in the OpenAPI schema processing of the agent import functionality in Amazon Bedrock AgentCore Starter Toolkit before 0.3.14 might allow an authenticated remote actor in the same AWS account to cause the environment of a user importing a Bedrock Agent to issue arbitrar...

PT-2026-107261

Name of the Vulnerable Software and Affected Versions Amazon Bedrock AgentCore Starter Toolkit versions prior to 0.3.14 Description Improper control of code generation within the agent import functionality allows an authenticated actor within the same account to execute arbitrary code. This occur...

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 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: Improper Validation of Specified Type of Input

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...

PT-2026-67789

Name of the Vulnerable Software and Affected Versions Amazon Bedrock AgentCore affected versions not specified Description Insufficient input validation in the AgentCore harness may allow an authenticated remote user to execute configured tools. This is achieved by using crafted content blocks in...

The Sub-10-Minute Cloud Takeover: How Exposed IAM Keys, Misconfiguration and AI Are Rewriting the Rules of Cloud Breaches

Key Takeaways Two real-world cloud attacks reached meaningful impact in less than ten minutes despite pursuing entirely different objectives. Both attackers treated the environment as a connected system, using existing permissions and relationships to expand their reach. Reconnaissance increasing...

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 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...

EUVD-2026-44988

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...