The #1 spot in the ranking is both more of a deal and less of a deal than it might appear. It's less of a deal in that HackerOne is an economic numbers game. There are countless programs you can sign up for, with varied difficulty levels and payouts. Most of them pay not a whole lot and don't attract top talent in the industry. Instead, they offer supplemental income to infosec-minded school-age kids in the developing world. So I wouldn't read this as "Xbow is the best bug hunter in the US". That's a bit of a marketing gimmick.

But this is also not a particularly meaningful objective. The problem is that there's a lot of low-hanging bugs that need squashing and it's hard to allocate sufficient resources to that. Top infosec talent doesn't want to do it (and there's not enough of it). Consulting companies can do it, but they inevitably end up stretching themselves too thin, so the coverage ends up being hit-and-miss. There's a huge market for tools that can find easy bugs cheaply and without too many false positives.

I personally don't doubt that LLMs and related techniques are well-tailored for this task, completely independent of whether they can outperform leading experts. But there are skeptics, so I think this is an important real-world result.

> To bridge that gap, we started dogfooding XBOW in public and private bug bounty programs hosted on HackerOne. We treated it like any external researcher would: no shortcuts, no internal knowledge—just XBOW, running on its own.

Is it dogfooding if you're not doing it to yourself? I'd considerit dogfooding only if they were flooding themselves in AI generated bug reports, not to other people. They're not the ones reviewing them.

Also, honest question: what does "best" means here? The one that has sent the most reports?

- Design the system and prompts

- Build and integrate the attack tools

- Guide the decision logic and analysis

This isn’t just semantics — overstating AI capabilities can confuse the public and mislead buyers, especially in high-stakes security contexts.

I say this as someone actively working in this space. I participated in the development of PentestGPT, which helped kickstart this wave of research and investment, and more recently, I’ve been working on Cybersecurity AI (CAI) — the leading open-source project for building autonomous agents for security:

- CAI GitHub: https://github.com/aliasrobotics/cai

- Tech report: https://arxiv.org/pdf/2504.06017

I’m all for pushing boundaries, but let’s keep the messaging grounded in reality. The future of AI in security is exciting — and we’re just getting started.

The future is definitely a combination of human and bots like anything else, it won't replace the humans just like coding bots won't replace devs. In fact this will allow humans to focus ob the fun/creative hacking instead of the basic/boring tests.

What I am worried about is on the triage/reproduction side, right now it is still mostly manual and it is a hard problem to automate.

https://hackerone.com/xbow?type=user

Which shows a different picture. This may not invalidate their claim (best US), but a screenshot can be a bit cherry-picked.

While niche and not widely used; there are at least thousands of publicly available servers for each of these projects.

I genuinely think this is one of the biggest near term issues with AI. Even if we get great AI "defence" tooling, there are just so many servers and (IoT or otherwise) devices out there, most of which is not trivial to patch. While a few niche services getting pwned isn't probably a big deal, a million niche services all getting pwned in quick succession is likely to cause huge disruption. There is so much code out there that hasn't been remotely security checked.

Maybe the end solution is some sort of LLM based "WAF" that inspects all traffic that ISPs deploy.

That seems a bit unethical. I’ve thought companies specifically deny usage of automated tools. A bit too late ey…?

https://en.wikipedia.org/wiki/Burning_Chrome

Yikes, explains why my manually submitted single vulnerability is taking weeks to triage.

The tooling and models are maturing quickly and there is definitely some value in autonomous security agents, both offensive and defensive- but also still requires alot of work, knowledge(my group is all ML people), skill, planning- if you want to approach anything more than bug bashing.

This recent paper from Dreadnode discusses a benchmark for this sort of challenge: https://arxiv.org/abs/2506.14682

But there's a claim that it is unsupervised, which I doubt. See how these two claims contradict each other.

>"XBOW is a fully autonomous AI-driven penetration tester. It requires no human input, "

>"To ensure accuracy, we developed the concept of validators, automated peer reviewers that confirm each vulnerability XBOW uncovers. Sometimes this process leverages a large language model; in other cases, we build custom programmatic checks."

I mean, I doubt you deploy this thing collecting thousands of dollars in bounties and you sit there twiddling your thumbs. Whatever work you put into the AI, whether fine tuned or generic and reusable, counts as supervised, and that's ok. Take the win, don't try to sell the automated dream to get investors or whatever, don't get caught up in fraud.

As I understand it, when you discover a type of vulnerabilities, it's very common to automate the detection and find other clients with such vulnerability, these are usually short lived and the well dries up fast, you need to constantly stay on top of the latest trends. I just don't buy that if you leave this thing unattended for even 3 months it would keep finding gold, that's a property of the engineers that is not scaleable (and that's ok).

The thing about bug bounties, the only way to win is to not play the game.

Like any "AI" article, this is an ad.

If you are willing to tolerate a high false positive rate, you can as well use Rational Purify or various analyzers.

Another great reading is [1](2024).

[1] "LLM and Bug Finding: Insights from a $2M Winning Team in the White House's AIxCC": https://news.ycombinator.com/item?id=41269791