Skip to content
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.

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

implement navigation similar to Juergens #4

Merged
merged 1 commit into from
Oct 18, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
17 changes: 17 additions & 0 deletions docs/examples/linux-priv-esc.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# Linux Privilege Escalation

These examples try to solve the following scenario:

- the attacker has low-level (non-`root`) access to a virtual machine through SSH.
- they know their username and the respective password
- and want to become the all powerful root user (`uid=0`)

## Example Implementations

These examples are currently available through our github repository:

| Example | Domain | Summary | Described in|
| -- | -- | -- | -- |
| [initial example](https://github.com/andreashappe/offensivegraphs/blob/main/src/initial_version.py) | linux priv-esc | good first example | [initial post](../blog/posts/2024-10-10-first-steps-and-initial-version.md), [tools and configuration](../blog/posts/2024-10-11-configuration-for-tool-calls.md) |
| [react agent](https://github.com/andreashappe/offensivegraphs/blob/main/src/switch-to-react.py) | linux priv-esc | use langgraph to reduce code | [Using `create_react_agent`](../blog/posts/2024-10-12-create_react_agent.md) |
| [plan-and-execute](https://github.com/andreashappe/offensivegraphs/blob/main/src/plan_and_execute.py) | linux priv-esc | multi-layer planing | [Adding Plan-and-Execute Planner](../blog/posts/2024-10-14-plan-and-exec.md) |
4 changes: 2 additions & 2 deletions docs/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -36,8 +36,8 @@ We see this as a benefit, we learn using LLMs and offensive security.

We document our journey through blog-posts that explain our prototypes and the decisions behind them:

- [Initial Journey and Exploration](blog/category/initial-journey/)
- [Planning and Decision-Making](blog/category/planning-and-decision-making/)
- [Security Agents with LangGraph](series/initial-journey.md)
- [Planning and Decision-Making](series/planning-and-decision-making.md)

## How to setup?

Expand Down
17 changes: 17 additions & 0 deletions docs/series/initial-journey.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# Security Agents with LangGraph

This is our initial foray into using LangChain/LangGraph for security agents. The blog series should be usable as an introduction for new developers that want to do something similiar.

## Basic Concepts

| Date | Blog Post | Description |
| --- | --- | --- |
| 10.10.2024 | [First Steps and Initial Version](./../blog/posts/2024-10-10-first-steps-and-initial-version.md) | Creating a first autonomous linux priv-esc agent using langgraph. Introduce `ssh connection` as Tool so that the agent can execute commands over SSH. |
| 11.10.2024 | [Improving Configuration Handling, esp. for Tools](./../blog/posts/2024-10-11-configuration-for-tool-calls.md) | Remove Hardcoded Configuration and improve Tool-Integration. |
| 12.10.2024 | [Simplify our Tool-Calling Agent through `create_react_agent`](./../blog/posts/2024-10-12-create_react_agent.md) | LangGraph offers a prebuilt react agent that highly simplifies our code (albeit does not allow us to further customize the agent flows). |

## Advanced Implementations

| Date | Blog Post | Description |
| --- | --- | --- |
| 14.10.2024 | [Adding Plan-and-Execute Planner](./../blog/posts/2024-10-14-plan-and-exec.md) | Implement the Plan-and-Execute pattern for pen-testing. This combines a high-level task list for pen-test planing with a low-level executor that tries to execute the given high-level task against a target virtual machine. |
7 changes: 7 additions & 0 deletions docs/series/planning-and-decision-making.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
# Planning and Decision Making

This series investigates multiple strategies that should guide security agent towards better coverage.

| Date | Blog Post | Description |
| --- | --- | --- |
| 14.10.2024 | [Adding Plan-and-Execute Planner](./../blog/posts/2024-10-14-plan-and-exec.md) | Implement the Plan-and-Execute pattern for pen-testing. This combines a high-level task list for pen-test planing with a low-level executor that tries to execute the given high-level task against a target virtual machine. |
7 changes: 7 additions & 0 deletions mkdocs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -41,3 +41,10 @@ extra:
analytics:
provider: google
property: G-XVEVXNXJ44
nav:
- 'Welcome to the Playground': index.md
- 'Examples':
- 'Linux Privilege Escalation': examples/linux-priv-esc.md
- 'Documentation Series:':
- 'Security Agents with LangGraph': series/initial-journey.md
- 'Planning and Decision Making': series/planning-and-decision-making.md