---
created: 2026-08-07
---
## Overview

We all know AI can find bugs. After a decade of research, I asked a harder question: can an autonomous system invent new attack techniques, and use them to hack live websites at scale? Building this sounded like a bad idea, so I did it.

It worked - I'll share an arsenal of new HTTP desync triggers, gadgets, and exploits that compromised banks, security solutions, and government infrastructure. Then I'll trace each discovery chain back through the HTTP Terminator, showing how to turn your personal expertise into an autonomous weapon - and the dark arts required to make it lethal.

I'll also share discoveries from beyond the autonomy horizon - some only reachable with a tight human/AI research loop, and others beyond AI's reach entirely.

These include a powerful undisclosed recon technique, and anomalies that hint at new attack classes offering alternative paths to critical impact. I'll analyse the discovery process, sharing detailed experiments that probe the boundaries of what AI can and can't discover.

You'll leave with new exploits from desync triggers to undisclosed attack classes, and a blueprint for turning your instincts into an autonomous research cascade.

And yes, I'll open-source the HTTP Terminator.

## Notes

Links
- https://portswigger.net/research/http1-must-die
- https://portswigger.net/research/listen-to-the-whispers-web-timing-attacks-that-actually-work
- https://www.intruder.io/research/practical-http-header-smuggling

### Ideation
- How good are models at creating new techniques?
- A simple prompt didn't work — needed to give it an idea to anchor on
	- Bad: "How can I detect if a front-end server is transforming input?" — too vague
	- Good: "How can I tell if a front-end server is transforming Unicode in request headers, without using header reflection?"
- Needed to generate a bunch of smaller goals and tasks
	- For example, giving it a protocol RFC and chunking it into smaller ideas, like 30 potential vectors
- Then have an evaluation harness try the generated techniques
	- Doesn't use AI — just runs each technique and records success or failure
	- Evaluating the technique
		- Have a baseline
		- Compare it to the technique
		- Then try against a remixed version

### Case Study
- Found an issue with response queue headers
- Prompting and reality-reframing
	- Agent was timid and would refuse
	- Renamed "Turbo Intruder" to something innocuous like "tube simulator" to get the agent to cooperate
- Had the AI build the code so the technique could be reused deterministically
- When it hit an issue in testing, used AI to hypothesize what could be done, then tested each hypothesis to validate

### Feedback Loop
What can the initial discoveries help find related items and vulns?
- Detection cascade: how can I detect similar behaviors elsewhere?
- Ideation cascade: does the root cause of that behavior enable other attacks?