### Summary The AWS Bedrock AgentCore Python SDK (bedrock-agentcore) is an open-source SDK that enables developers to build, deploy, and manage agents on AWS Bedrock AgentCore. An issue exists in the install_packages() method of the Code Interpreter client where crafted package name arguments can bypass input validation and allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox. ### Impact The install_packages() method constructs a 'pip install' shell command executed within the Code Interpreter sandbox using package name arguments provided by the caller. The method applied an incomplete blocklist that allowed crafted package name arguments - specifically pip flags such as '--index-url' and '-r' - to pass validation unchecked. A remote authenticated user who can influence the arguments passed to install_packages() could redirect package resolution to a third-party-controlled PyPI server, or expose the contents of arbitrary sandbox files and environment variables. **Impacted versions:** AWS Bedrock AgentCore Python SDK (bedrock-agentcore) versions >= 1.1.3 and < 1.6.1 ### Patches This issue has been addressed in bedrock-agentcore version 1.6.1. We recommend upgrading to the latest version and ensuring any forked or derivative code is patched to incorporate the new fixes. ### Workarounds If you are unable to upgrade immediately, avoid passing any user-supplied or externally-influenced strings directly to install_packages(). Restrict calls to a fixed, hardcoded list of approved package names within your application code. ### References If you have any questions or comments about this advisory, we ask that you contact AWS Security via our [vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting) or directly via email to [[email protected]](mailto:[email protected]). Please do not create a public GitHub issue. We would like to thank Sergio Garcia for collaborating on this issue through the coordinated vulnerability disclosure process.
### Summary The AWS Bedrock AgentCore Python SDK (bedrock-agentcore) is an open-source SDK that enables developers to build, deploy, and manage agents on AWS Bedrock AgentCore. An issue exists in the install_packages() method of the Code Interpreter client where crafted package name arguments can bypass input validation and allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox. ### Impact The install_packages() method constructs a 'pip install' shell command executed within the Code Interpreter sandbox using package name arguments provided by the caller. The method applied an incomplete blocklist that allowed crafted package name arguments - specifically pip flags such as '--index-url' and '-r' - to pass validation unchecked. A remote authenticated user who can influence the arguments passed to install_packages() could redirect package resolution to a third-party-controlled PyPI server, or expose the contents of arbitrary sandbox files and environment variables. **Impacted versions:** AWS Bedrock AgentCore Python SDK (bedrock-agentcore) versions >= 1.1.3 and < 1.6.1 ### Patches This issue has been addressed in bedrock-agentcore version 1.6.1. We recommend upgrading to the latest version and ensuring any forked or derivative code is patched to incorporate the new fixes. ### Workarounds If you are unable to upgrade immediately, avoid passing any user-supplied or externally-influenced strings directly to install_packages(). Restrict calls to a fixed, hardcoded list of approved package names within your application code. ### References If you have any questions or comments about this advisory, we ask that you contact AWS Security via our [vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting) or directly via email to [[email protected]](mailto:[email protected]). Please do not create a public GitHub issue. We would like to thank Sergio Garcia for collaborating on this issue through the coordinated vulnerability disclosure process.
Update bedrock-agentcore to 1.6.1 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanImproper neutralization of argument delimiters in AWS Bedrock AgentCore Python SDK install_packages() affects bedrock-agentcore (pip). Severity is high. ### Summary The AWS Bedrock AgentCore Python SDK (bedrock-agentcore) is an open-source SDK that enables developers to build, deploy, and manage agents on AWS Bedrock AgentCore. An issue exists in the install_packages() method of the Code Interpreter client where crafted package name arguments can bypass input validation and allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox. ### Impact The install_packages() method constructs a 'pip install' shell command executed within the Code Interpreter sandbox using package name arguments provided by the caller. The method applied an incomplete blocklist that allowed crafted package name arguments - specifically pip flags such as '--index-url' and '-r' - to pass validation unchecked. A remote authenticated user who can influence the arguments passed to install_packages() could redirect package resolution to a third-party-controlled PyPI server, or expose the contents of arbitrary sandbox files and environment variables. **Impacted versions:** AWS Bedrock AgentCore Python SDK (bedrock-agentcore) versions >= 1.1.3 and < 1.6.1 ### Patches This issue has been addressed in bedrock-agentcore version 1.6.1. We recommend upgrading to the latest version and ensuring any forked or derivative code is patched to incorporate the new fixes. ### Workarounds If you are unable to upgrade immediately, avoid passing any user-supplied or externally-influenced strings directly to install_packages(). Restrict calls to a fixed, hardcoded list of approved package names within your application code. ### References If you have any questions or comments about this advisory, we ask that you contact AWS Security via our [vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting) or directly via email to [[email protected]](mailto:[email protected]). Please do not create a public GitHub issue. We would like to thank Sergio Garcia for collaborating on this issue through the coordinated vulnerability disclosure process.
AI coding agents often install or upgrade packages automatically in pip. A high vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
| Package | Affected range | Fixed version |
|---|---|---|
| bedrock-agentcorepip | >=1.1.3,<1.6.1 | 1.6.1 |
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL GuardUpdate bedrock-agentcore to 1.6.1 if you use the affected versions. Test the change in a non-production environment first.
Local check
hol-guard supply-chain scanImproper neutralization of argument delimiters in AWS Bedrock AgentCore Python SDK install_packages() affects bedrock-agentcore (pip). Severity is high. ### Summary The AWS Bedrock AgentCore Python SDK (bedrock-agentcore) is an open-source SDK that enables developers to build, deploy, and manage agents on AWS Bedrock AgentCore. An issue exists in the install_packages() method of the Code Interpreter client where crafted package name arguments can bypass input validation and allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox. ### Impact The install_packages() method constructs a 'pip install' shell command executed within the Code Interpreter sandbox using package name arguments provided by the caller. The method applied an incomplete blocklist that allowed crafted package name arguments - specifically pip flags such as '--index-url' and '-r' - to pass validation unchecked. A remote authenticated user who can influence the arguments passed to install_packages() could redirect package resolution to a third-party-controlled PyPI server, or expose the contents of arbitrary sandbox files and environment variables. **Impacted versions:** AWS Bedrock AgentCore Python SDK (bedrock-agentcore) versions >= 1.1.3 and < 1.6.1 ### Patches This issue has been addressed in bedrock-agentcore version 1.6.1. We recommend upgrading to the latest version and ensuring any forked or derivative code is patched to incorporate the new fixes. ### Workarounds If you are unable to upgrade immediately, avoid passing any user-supplied or externally-influenced strings directly to install_packages(). Restrict calls to a fixed, hardcoded list of approved package names within your application code. ### References If you have any questions or comments about this advisory, we ask that you contact AWS Security via our [vulnerability reporting page](https://aws.amazon.com/security/vulnerability-reporting) or directly via email to [[email protected]](mailto:[email protected]). Please do not create a public GitHub issue. We would like to thank Sergio Garcia for collaborating on this issue through the coordinated vulnerability disclosure process.
AI coding agents often install or upgrade packages automatically in pip. A high vulnerability in a dependency can be pulled into a project through a normal install or update without a human reviewing the change, expanding the blast radius from a single package to every agent workspace that depends on it.
| Package | Affected range | Fixed version |
|---|---|---|
| bedrock-agentcorepip | >=1.1.3,<1.6.1 | 1.6.1 |
Fixed versions are reported by the source feed; confirm compatibility before updating.
Reported by GitHub Security Advisories (ghsa).
HOL Guard can help your team review package activity against supported protection paths.
Explore HOL Guard