Skip to content

Commit 842b3ed

Browse files
andreashappeandreashappe
authored
Merge pull request #118 from ipa-lab/development
bump dependencies and add Qsan1's documentation
2 parents 7a79d22 + 5ef2ab7 commit 842b3ed

File tree

4 files changed

+14
-12
lines changed

4 files changed

+14
-12
lines changed

‎README.md‎

Lines changed: 9 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,7 @@ If you want to use hackingBuddyGPT and need help selecting the best LLM for your
1515

1616
## hackingBuddyGPT in the News
1717

18+
- 2025-04-08: [Andreas Happe](https://github.com/andreashappe) presented hackingBuddyGPT at the [Google Developer Group TU Wien](https://www.linkedin.com/company/google-developer-group-tu-wien/)
1819
- 2024-11-20: [Manuel Reinsperger](https://www.github.com/neverbolt) presented hackingBuddyGPT at the [European Symposium on Security and Artificial Intelligence (ESSAI)](https://essai-conference.eu/)
1920
- 2024-07-26: The [GitHub Accelerator Showcase](https://github.blog/open-source/maintainers/github-accelerator-showcase-celebrating-our-second-cohort-and-whats-next/) features hackingBuddyGPT
2021
- 2024-07-24: [Juergen](https://github.com/citostyle) speaks at [Open Source + mezcal night @ GitHub HQ](https://lu.ma/bx120myg)
@@ -53,6 +54,7 @@ Over time, more contributors joined:
5354
- Juergen Cito, [github](https://github.com/citostyle), [linkedin](https://at.linkedin.com/in/jcito), [twitter/x](https://twitter.com/citostyle), [Google Scholar](https://scholar.google.ch/citations?user=fj5MiWsAAAAJ&hl=en)
5455
- Manuel Reinsperger, [github](https://github.com/Neverbolt), [linkedin](https://www.linkedin.com/in/manuel-reinsperger-7110b8113/), [twitter/x](https://twitter.com/neverbolt)
5556
- Diana Strauss, [github](https://github.com/DianaStrauss), [linkedin](https://www.linkedin.com/in/diana-s-a853ba20a/)
57+
- Benjamin Probst, [github](https://github.com/Qsan1)
5658

5759
## Existing Agents/Usecases
5860

@@ -63,13 +65,13 @@ Our initial forays were focused upon evaluating the efficiency of LLMs for [linu
6365
privilege escalation attacks](https://arxiv.org/abs/2310.11409) and we are currently breaching out into evaluation
6466
the use of LLMs for web penetration-testing and web api testing.
6567

66-
| Name | Description | Screenshot |
67-
|--------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|
68-
| [minimal](https://docs.hackingbuddy.ai/docs/dev-guide/dev-quickstart) | A minimal 50 LoC Linux Priv-Esc example. This is the usecase from [Build your own Agent/Usecase](#build-your-own-agentusecase) | ![A very minimal run](https://docs.hackingbuddy.ai/run_archive/2024-04-29_minimal.png) |
69-
| [linux-privesc](https://docs.hackingbuddy.ai/docs/usecases/linux-priv-esc) | Given an SSH-connection for a low-privilege user, task the LLM to become the root user. This would be a typical Linux privilege escalation attack. We published two academic papers about this: [paper #1](https://arxiv.org/abs/2308.00121) and [paper #2](https://arxiv.org/abs/2310.11409) | ![Example wintermute run](https://docs.hackingbuddy.ai/run_archive/2024-04-06_linux.png) |
70-
| [web-pentest (WIP)](https://docs.hackingbuddy.ai/docs/usecases/web) | Directly hack a webpage. Currently in heavy development and pre-alpha stage. | ![Test Run for a simple Blog Page](https://docs.hackingbuddy.ai/run_archive/2024-05-03_web.png) |
71-
| [web-api-pentest (WIP)](https://docs.hackingbuddy.ai/docs/usecases/web-api) | Directly test a REST API. Currently in heavy development and pre-alpha stage. (Documentation and testing of REST API.) | Documentation:![web_api_documentation.png](https://docs.hackingbuddy.ai/run_archive/2024-05-15_web-api_documentation.png) Testing:![web_api_testing.png](https://docs.hackingbuddy.ai/run_archive/2024-05-15_web-api.png) |
72-
68+
| Name | Description | Screenshot |
69+
|------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
70+
| [minimal](https://docs.hackingbuddy.ai/docs/dev-guide/dev-quickstart) | A minimal 50 LoC Linux Priv-Esc example. This is the usecase from [Build your own Agent/Usecase](#build-your-own-agentusecase) | ![A very minimal run](https://docs.hackingbuddy.ai/run_archive/2024-04-29_minimal.png) |
71+
| [linux-privesc](https://docs.hackingbuddy.ai/docs/usecases/linux-priv-esc) | Given an SSH-connection for a low-privilege user, task the LLM to become the root user. This would be a typical Linux privilege escalation attack. We published two academic papers about this: [paper #1](https://arxiv.org/abs/2308.00121) and [paper #2](https://arxiv.org/abs/2310.11409) | ![Example wintermute run](https://docs.hackingbuddy.ai/run_archive/2024-04-06_linux.png) |
72+
| [web-pentest (WIP)](https://docs.hackingbuddy.ai/docs/usecases/web) | Directly hack a webpage. Currently in heavy development and pre-alpha stage. | ![Test Run for a simple Blog Page](https://docs.hackingbuddy.ai/run_archive/2024-05-03_web.png) |
73+
| [web-api-pentest (WIP)](https://docs.hackingbuddy.ai/docs/usecases/web-api) | Directly test a REST API. Currently in heavy development and pre-alpha stage. (Documentation and testing of REST API.) | Documentation:![web_api_documentation.png](https://docs.hackingbuddy.ai/run_archive/2024-05-15_web-api_documentation.png) Testing:![web_api_testing.png](https://docs.hackingbuddy.ai/run_archive/2024-05-15_web-api.png) |
74+
| [extended linux-privesc](https://docs.hackingbuddy.ai/docs/usecases/extended-linux-privesc) | This usecases extends linux-privesc with additional features such as retrieval augmented generation (RAG) or chain-of-thought (CoT) | ![Extended Linux Privilege Escalation Run](https://docs.hackingbuddy.ai/run_archive/2025-4-14_extended_privesc_usecase_1.png) ![Extended Linux Privilege Escalation Run](https://docs.hackingbuddy.ai/run_archive/2025-4-14_extended_privesc_usecase_1.png) |
7375
## Build your own Agent/Usecase
7476

7577
So you want to create your own LLM hacking agent? We've got you covered and taken care of the tedious groundwork.

‎pyproject.toml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,7 @@ dependencies = [
4141
'nltk',
4242
'fastapi == 0.114.0',
4343
'fastapi-utils == 0.7.0',
44-
'jinja2 == 3.1.4',
44+
'jinja2 == 3.1.6',
4545
'uvicorn[standard] == 0.30.6',
4646
'dataclasses_json == 0.6.7',
4747
'websockets == 13.1',

‎src/hackingBuddyGPT/usecases/rag/README.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,10 +2,10 @@
22
This usecase is an extension of `usecase/privesc`.
33

44
## Setup
5-
### Depdendencies
5+
### Dependencies
66
The needed dependencies can be downloaded with `pip install -e '.[rag-usecase]'`. If you encounter the error `unexpected keyword argument 'proxies'` after trying to start the usecase, try downgrading `httpx` to 0.27.2.
77
### RAG vector store setup
8-
The code for the vector store setup can be found in `rag_utility.py`. Currently the vectore store uses two sources: `GTFObins` and `hacktricks`. To use RAG, download the markdown files and place them in `rag_storage/GTFObinMarkdownfiles` (`rag_storage/hacktricksMarkdownFiles`). You can download the markdown files either from the respective github repository ([GTFObin](https://github.com/GTFOBins/GTFOBins.github.io/tree/master), [hacktricks](https://github.com/HackTricks-wiki/hacktricks/tree/master/src/linux-hardening/privilege-escalation)) or scrape them from their website ([GTFObin](https://gtfobins.github.io/), [hacktricks](https://book.hacktricks.wiki/en/linux-hardening/privilege-escalation/index.html)).
8+
The code for the vector store setup can be found in `rag_utility.py`. Currently the vector store uses two sources: `GTFObins` and `hacktricks`. To use RAG, download the markdown files and place them in `rag_storage/GTFObinMarkdownfiles` (`rag_storage/hacktricksMarkdownFiles`). You can download the markdown files either from the respective github repository ([GTFObin](https://github.com/GTFOBins/GTFOBins.github.io/tree/master), [hacktricks](https://github.com/HackTricks-wiki/hacktricks/tree/master/src/linux-hardening/privilege-escalation)) or scrape them from their website ([GTFObin](https://gtfobins.github.io/), [hacktricks](https://book.hacktricks.wiki/en/linux-hardening/privilege-escalation/index.html)).
99

1010
New data sources can easily be added by adjusting `initiate_rag()` in `rag_utility.py`.
1111

‎src/hackingBuddyGPT/utils/openai/openai_llm.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -62,10 +62,10 @@ def get_response(self, prompt, *, retry: int = 0,azure_retry: int = 0, **kwargs)
6262
print("Received 408 Status Code, trying again.")
6363
return self.get_response(prompt, azure_retry = azure_retry + 1)
6464
else:
65-
raise Exception(f"Error from Gateway ({response.status_code}")
65+
raise Exception(f"Error from Gateway ({response.status_code})")
6666

6767
if response.status_code != 200:
68-
raise Exception(f"Error from OpenAI Gateway ({response.status_code}")
68+
raise Exception(f"Error from OpenAI Gateway ({response.status_code})")
6969

7070
except requests.exceptions.ConnectionError:
7171
print("Connection error! Retrying in 5 seconds..")

0 commit comments

Comments
 (0)