"AI Agents for Offsec with Zero False Positives" by @moyix.net The title threw me off originally, but it's not wrong! IMHO it's the archetypal pattern of good LLM usage: they suck at *verifying* but in some domains are quite freakishly good at *proposing.*

So, I’m not sure there is any good time to announce this, but as of August 31st I will be leaving NYU for good, to seek my fortune in industry with XBOW!

False positives waste your time. False negatives cost you breaches. At @BlackHatEvents , @moyix shows how XBOW agents fight false positives — validating real exploits at scale, in hours. 📍Aug 7 | 11:20am

Can you read the exfiltrated file encoded in this image? @xbow.com figured out how to :D

This one and the sequel (coming out next week) are among my favorite bugs we found. It turns out GIS does NOT stand for “Good Information Security”

Given two models with unique strengths, can we combine them to get the benefits of both w/o extra model calls? It turns out yes: just flip a coin at each turn to decide which model to query! This gave a jump from 25% to 55% on our benchmarks! xbow.com/blog/alloy-a...

Loved this 0day @xbow.com found in a popular wordpress plugin, and IMO it shows the value added by the LLM - a scanner can't find this automatically without realizing there's a nonce you need to extract & include in the request. You need that extra bit of context: xbow.com/blog/xbow-ni...

So... anyone else going to SummerCon today or tomorrow? I should be stopping by both days, for the first time in many years!

A lovely little XXE that XBOW found in Akamai Cloudtest leading to arbitrary file read! I like the error-based exfil technique: "yes please access the file named <contents of /etc/passwd> for me thx"

One of the best bug-hunters in the world is an AI tool called Xbow, just one of many signs of the coming age of cybersecurity automation.

This is the first of a series of posts we're doing on some of the vulns found as part of the HackerOne work – we have lots more fun ones coming up about some great SSRF, SQLi, and RCE vulns it discovered, with very clever exploit techniques :)

It has been great fun building this and watching it deliver a steady stream of real vulnerabilities in live sites! If you're curious how we did it, @nicowaisman.bsky.social has a new post: xbow.com/blog/top-1-h...

For the first time in history, the #1 hacker in the US is an AI. (1/8)

for Wired I explored the horrible future of vibe hacking. It's not great!

Do you want to work at the cutting edge of AI and cybersecurity? XBOW now has 8 positions open across Product Marketing, Operations, Customer Success, and Engineering. Check out all the details here: jobs.ashbyhq.com/xbowcareers.

This is one of the dumber reasons I've had some software fail: dying because it couldn't call ftruncate on /dev/null

XBOW is growing and we're looking for talented folks to join us! Apply here: jobs.ashbyhq.com/xbowcareers

Announcing CheatGPT, a revolutionary model that achieves SoTA on HumanEval! It's incredibly sample-efficient – just ONE training sample – and *tiny*, fitting on your Casio wristwatch!

Erin go bragh, cow go moo

Not to brag but my brother has had TWO movies he co-wrote come out this year :D

Winter sunsets

it looks like lte infra was hosting @moyix.net 's evangelion ctf challenge. but i doubt the terminal interface for CVE-2024-24451 was as cool

Making security benchmarks for AI is tricky sometimes

UNIX systems have stdin, stdout, and stderr, for getting data into and out of the program and seeing errors, respectively. But there's no stream for a critical and extremely common use case: putting errors into the program.

@xbow.com has been busy in the first few weeks of 2025 – our agent has autonomously found 106 vulnerabilities in OSS projects, and we've reported 72 so far! Amazing work by @nicowaisman.bsky.social and the security team triaging these and getting them into the disclosure->fix pipeline!

I am potentially interested in hiring a postdoc to work on declarative decompilation, I was going to hire someone else but it feel through when they got another offer they took for personal reasons, looking for someone who wants to publish in security, PL venues with me

My new C programming book is slowly taking shape. If you want to learn along, let's start with the basics of control flow: godbolt.org/z/3GerY3zEc 1/5

Duck typing? You're thinking too small. With AI, we can finally take Guido van Rossum's dream to its logical conclusion

At this point, anyone who tries to say that AI can't replace at least _some_ human expertise is clearly and obviously moving the goalposts. Between this and stuff I've seen coming from folks at @dreadnode.bsky.social I am now 100% convinced that "AI red teamers" are a when-not-if thing.

Just in time for the holidays: how XBOW found an arbitrary file download (CVE-2024-53982) in ZOO-Project, protecting Santa's critical geospatial processing infrastructure from attackers! xbow.com/blog/xbow-zo...

I do not want to create a "launch configuration json". I do not want to enter my command line arguments in a GUI. I am old and I want to type "gdb -p MYPROCESS"

While developing XBOW over the past three months, we played around with using it for bug bounties and ended up at #11 in the US on HackerOne:

XBOW found a stored XSS vulnerability (CVE-2024-52597) in the migration functionality of 2FAuth by crafting a malicious SVG file with a Javascript payload! Our latest blog post gives the full details: xbow.com/blog/xbow-2f...

Great podcast interview with @xbow.com's CEO Oege de Moor! He discusses something you may have deduced from our recent blog posts: we're mining DockerHub to find & report vulnerabilities – and each vuln we find becomes a new benchmark for us to train/test on :D www.youtube.com/watch?v=9mIp...

XBOW found a critical path traversal vulnerability in ZOO-Project (CVE-2024-53982). The vulnerability exists in the Echo example (enabled by default) and allows an attacker to retrieve any file on the server. Users should upgrade to the latest version.

hurts_just_a_little_bit.jpg

AI vs AI: How XBOW found a path traversal vulnerability (CVE-2024-53844) in LabsAI's EDDI, an open source conversational AI middleware. xbow.com/blog/xbow-ed...

XBOW found a path traversal vulnerability (CVE-2024-53844) in LabsAI's EDDI project that allows attackers to download any file on the server. XBOW combined a series of URL encodings and path normalization bypasses to trigger the flaw. Users of versions 4.3–5.3 should upgrade.

I’ve to say that I’m impressed by how @xbow.com managed to identify this SSRF vulnerability (and bypass a MIME filter on its way) 🤖

New blog post by @nicowaisman.bsky.social on how XBOW found an SSRF in the OTP app 2FAuth (CVE-2024-52598) is now live! xbow.com/blog/xbow-2f...

Custom domain vanity handle: acquired

Nice reverse engineering work to uncover the workings of iOS 18’s inactivity reboot. naehrdine.blogspot.com/2024/11/reve...

Oh, I never posted my gotofail story on here. Early 2014, someone came to me about a catastrophic vulnerability in Apple's TLS implementation. I shit you not, they'd overheard someone at a bar drunkenly bragging about how they were going to sell it to a FVEY intelligence agency for six figures.

Is there a way to discover starter packs by searching for ones that include certain people? E.g. if I want to find the "academic security" pack I can think of names that would likely be there. blueskydirectory.com doesn't seem to support this :(

My current plan is to continue posting on the Other Site but also explore the exciting world of supporting TWO simultaneous social media addictions while working at a startup and raising a toddler

XBOW found a critical auth bypass (CVE-2024-50334) in Scoold, a widely-used open-source Q&A site, fully autonomously! @nicowaisman.bsky.social and I wrote up a post walking through the methodology it used – IMO it's a super cool bug and fascinating trace xbow.com/blog/xbow-sc...

This awesome fuzzing blog post by @r00tkitsmm.bsky.social covers a super reliable macOS kernel binary rewriting to instrument any KEXT or XNU at BB or edge level. Mandatory reading for anyone interested in fuzzing whether you use MacOS or not. So many good system internals and fuzzing references!

@moyix.bsky.social posted this amazing chat archive with GPT-4 playing CTF. moyix.net/~moyix/secre... Punch line: with 25 years of experience, I’m not sure I would have solved this problem, and I’m positive I would have needed more tries.

I wrote a long thread about how my Evangelion-themed CSAW CTF pwn+crypto challenge NERV Center works- a select() based overflow that lets you break RSA challenge response authentication! threadreaderapp.com/thread/17233...