Skip to content

Add a security disclaimer for agentic memory #11407

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −0
Open

Add a security disclaimer for agentic memory #11407

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions _ml-commons-plugin/agentic-memory.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,13 @@
Currently, agentic memory is designed for integration with external agent frameworks like LangChain and LangGraph. OpenSearch's internal [agents]({{site.url}}{{site.baseurl}}/ml-commons-plugin/agents-tools/agents/) cannot interact with agentic memory.
{: .note}

## Disclaimer
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
## Disclaimer

Please be advised that the Agentic Memory capability within OpenSearch is provided as a **framework** designed to empower developers to build and manage memory for AI agents. As the administrator or owner of a memory container, you are solely responsible for the configuration, management, and security of your implementation.

Check warning on line 26 in _ml-commons-plugin/agentic-memory.md

View workflow job for this annotation

GitHub Actions / style-job 

[vale] reported by reviewdog 🐶
[OpenSearch.Please] Using 'Please' is unnecessary. Remove.

Raw Output:
{"message": "[OpenSearch.Please] Using 'Please' is unnecessary. Remove.", "location": {"path": "_ml-commons-plugin/agentic-memory.md", "range": {"start": {"line": 26, "column": 1}}}, "severity": "WARNING"}
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Please be advised that the Agentic Memory capability within OpenSearch is provided as a **framework** designed to empower developers to build and manage memory for AI agents. As the administrator or owner of a memory container, you are solely responsible for the configuration, management, and security of your implementation.
The agentic memory capability in OpenSearch is provided as a framework that enables you to build and manage memory for AI agents. As the administrator or owner of a memory container, you are responsible for the configuration, management, and security of your implementation.

Specifically, you are responsible for the following:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Specifically, you are responsible for the following:
You are responsible for the following:

1. **Data Access Control:** You are responsible for implementing and enforcing all necessary data access controls for the conversation data stored within the memory container. This includes, but is not limited to, configuring appropriate index-level permissions, document-level security (DLS), or other mechanisms to restrict access. This responsibility is especially critical when the use_system_index option is set to false, as data will be stored in a standard index that requires explicit permission management.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
1. **Data Access Control:** You are responsible for implementing and enforcing all necessary data access controls for the conversation data stored within the memory container. This includes, but is not limited to, configuring appropriate index-level permissions, document-level security (DLS), or other mechanisms to restrict access. This responsibility is especially critical when the use_system_index option is set to false, as data will be stored in a standard index that requires explicit permission management.
- Data access control: Implement and enforce all necessary data access controls for the conversation data stored within the memory container. This includes, but is not limited to, configuring appropriate index-level permissions, document-level security (DLS), or other mechanisms to restrict access. This responsibility is especially critical when the use_system_index option is set to false, because data will be stored in a standard index that requires explicit permission management.

2. **Custom System Prompt Management:** If you opt to use a customized system prompt instead of the default, you are solely responsible for the content, management, and behavior of that prompt. OpenSearch is not responsible for the outputs or interactions resulting from user-defined system prompts.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
2. **Custom System Prompt Management:** If you opt to use a customized system prompt instead of the default, you are solely responsible for the content, management, and behavior of that prompt. OpenSearch is not responsible for the outputs or interactions resulting from user-defined system prompts.
- Custom system prompt management: If you choose to use a customized system prompt instead of the default, you are responsible for the content, management, and behavior of that prompt. OpenSearch is not responsible for the outputs or interactions resulting from user-defined system prompts.

Failure to properly configure and secure your Agentic Memory implementation may result in unauthorized data access, data leakage, or unintended agent behavior.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Failure to properly configure and secure your Agentic Memory implementation may result in unauthorized data access, data leakage, or unintended agent behavior.
Failure to properly configure and secure your agentic memory implementation may result in unauthorized data access, data leakage, or unintended agent behavior.


## Memory containers

Agentic memory is organized into _memory containers_ that hold all memory types for a specific use case, such as a chatbot, research assistant, or customer service agent.
Expand Down
Loading