Integration proposal: HOL Guard pre-tool security plugin

## Context

`google/adk-python#6886` was closed with an explicit redirect here because the core ADK repository does not plan to support third-party tools directly.

I’m proposing a small community plugin for HOL Guard in this repository’s existing `src/google/adk_community/plugins` surface, rather than a core ADK change.

## Proposed integration

A `HolGuardPlugin(BasePlugin)` would use ADK’s existing `before_tool_callback` boundary for command-bearing tools on supported local execution paths.

The intended contract is deliberately fail-closed:

- inspect the validated tool name/arguments with HOL Guard before downstream execution;
- proceed only for an explicitly benign HOL Guard result;
- review/risky/unknown/error paths short-circuit before the protected tool executes;
- allow paths delegate exactly once;
- no Guard Cloud dependency is required for the local enforcement path.

The implementation would stay scoped to tools whose arguments can be represented as a command/action HOL Guard actually understands. It would not claim interception of unrelated hosted/control-plane operations.

## Validation

If maintainers are comfortable with this placement, I’d include focused unit tests covering:

- deny/review/error -> zero downstream executions;
- allow -> exactly one downstream execution;
- unsupported/non-command tools -> explicit, documented behavior;
- a small reproducible E2E example using the ADK runner/plugin path.

I did not find an existing HOL Guard issue or PR in this repository. Per `CONTRIBUTING.md`, I’m opening the issue first and will wait for maintainer direction before implementing.

Affiliation: I’m contributing on behalf of Hashgraph Online / HOL Guard.

Bắt đầu bằng việc đọc CONTRIBUTING.md và các plugin hiện có trong src/google/adk_community/plugins, sau đó lần theo before_tool_callback của ADK và đường dẫn runner/plugin. Đề xuất này đã sẵn sàng để maintainer định hướng thay vì triển khai; để hoàn tất, cần có phạm vi được phê duyệt, các unit test tập trung cho hành vi deny/review/error và allow, tài liệu về hành vi đối với các tool không được hỗ trợ, cùng một ví dụ E2E nhỏ có thể tái lập.

Do mô hình lập chỉ mục viết ra từ nội dung của issue.