IntruderPayloads VS SQLMap

It's very interesting that AppSec may now begin to include "prompt injection" attacks as something of relevance.

Specifically with libraries like LangChain[0] that allow for you to perform complex actions ("What's the weather?" -> makes HTTP request to fetch weather) then we end up in a world where injection attacks can have side effects with security implications.

I've been thinking about what security might look like for a post-ChatGPT world and how I'd attempt to defend against it. I'd probably start by building a database of attack prompts, kind of like this[1] fuzz list but for AI, then I'd train a second neural net that acts like an adversarial neural network[2] to try to exploit the system based on those payloads. The end result would sort of like SQLMap[3] but for AI systems where it can automatically "leak" hidden prompts and potentially find "bypasses" to escape the sandbox.

Has anybody else spent any time thinking about how to defend systems against prompt injection attacks that have possible side effects (like making an HTTP request)?

0: https://langchain.readthedocs.io/en/latest/modules/agents/ex...

1: https://github.com/1N3/IntruderPayloads

2: https://en.wikipedia.org/wiki/Generative_adversarial_network

3: https://sqlmap.org/

nmap, hacktricks and burpsuite are my best friend on enumeration. Search every port on hacktricks, fuzz every field in your web request on burpsuite using https://github.com/1N3/IntruderPayloads. Don't forget to try bruteforce if everything failed.

sqlmap

A few weeks ago, I took a short cyber security course on Udemy. SQL injection was a section of the course. I knew about the concept though, I hadn't tried it. I was planning to make a Restful API server and tried SQL injection using a tool sqlmap, which was introduced in the course. While I could have used existing server code, I decided to build one from scratch. It's been a while since I worked on a Restful API server, and I wanted to refresh my knowledge for learning purposes.

I recommend looking for an alternative or if you must do it this way test it with https://sqlmap.org to make sure you are not vulnerable to the lowest effort attacks.

The DAST checks can be automated up to a certain point, where the code should be able to withstand certain scans and attacks. For eg. SQL Injections can be checked with sqlmap which tests with each and every type of sql injection payload and reports it back to the user.

git clone --depth 1 https://github.com/sqlmapproject/sqlmap.git sqlmap-dev

Sounds good, why not try making a simple vulnerability scanner for APIs too? Maybe something similar to SQLMap

Its not that much of a tool than wrappers of few awesome tools that most of you probably know and use today - sqlmap, bbot and nikto.

I'm excited to share with you my latest contributions to the GitHub community: a collection of free GitHub Actions designed to streamline and enhance security practices utilizing DAST and OSINT tooling that is widely used - sqlmap, bbot and nikto. There were no GH Actions that I could find, so I made them for my use case, but figured everyone can benefit from those awesome tools.

SQLMap