@[email protected]

Improving the world’s security at Google. Opinions are mine.

[@[email protected] @SecurityMB]

We just published two blog posts about PageBreak, Google's AI web security scanner (that I've helped develop for the better part of the year). We share our approach and a couple of findings, enjoy!

- https://t.co/94YQt7uTGU
- https://t.co/NG9EoC4r7x

[Google VRP (Google Bug Hunters) @GoogleVRP]

Introducing PageBreak, an agentic vulnerability discovery tool using deterministic validation to achieve a near-zero false positive rate.

How it works: https://t.co/n3k4vvNhoq

For real-world vulnerabilities PageBreak has discovered 👇

https://t.co/0pZ5rWoWw2

[Harsh Jaiswal @rootxharsh]

“And no, AI isn't perfect. But Christ, anybody who points to the problems at AI had better be looking in the mirror and pointing at themselves at the same time.

Because it's not like natural intelligence is always all that great either.”

https://t.co/1ygFz1g1Ib

[@[email protected] @SecurityMB]

@S1r1u5_ Thanks for the appreciation!

In theory this could be findable by just reading the HTML spec but I assume that would be difficult for agents. But if they can fiddle with the HTML and fuzz it, I’d expect them to be able to discover it.

[@[email protected] @SecurityMB]

@kinugawamasato I remember stumbling upon that when doing my copy&paste research a few years ago. AFAIR there was something similar in one of macOS built in apps but I don’t remember which one.

[@[email protected] @SecurityMB]

This is a really awesome summary of how to approach bypassing HTML sanitizers, I highly recommend to check this out!

[Masato Kinugawa @kinugawamasato]

DOMPurifyバイパスの歴史をまとめたページ。HTMLサニタイザーバイパスのノウハウがぎっしり詰まってる。
特に今年に入ってから発見された<selectedcontent>のバイパスは驚いた
https://t.co/PNPSorjJEL

[terjanq @terjanq]

Have been working on agentic vulnerability discovery for a while now, happy to share about CodeMender! 🚀🚀

[@[email protected] @SecurityMB]

Anyone I know interested in joining the Google Security Team in Zurich? Let me know, I can give a referral :D

Here's the job posting: https://t.co/yH2iUotLGV

[@[email protected] @SecurityMB]

@sudhanshur705 @kevin_mizu Cool research and nice write up! Also thanks for the shout outs!

Side note: I’m actually planning to propose yet another spec change this year to try to kill even more mXSS-es so enjoy them while you can 😅

[@[email protected] @SecurityMB]

That must be the worst captcha I’ve ever seen.

[@[email protected] @SecurityMB]

That was a nice bug, thanks for the shoutout!

[Intigriti @intigriti]

2️⃣ XSS in GMail's AMP4Email via DOM Clobbering

Michał Bentkowski (@SecurityMB) exploited DOM clobbering to achieve XSS in Gmail's AMP4Email feature. Found that AMP4Email allowed id attributes, which could be leveraged to overwrite JavaScript variables and bypass Google's strict security filters.

https://t.co/7cqKL9oFjm

[Jun Kokatsu @shhnjk]

Why the "Agents Rule of Two" is flawed
https://t.co/GLVIcyFbEt

[@[email protected] @SecurityMB]

@gridogram I forgot to play gridogram yesterday. Is there an option to play yesterday's puzzle?

[Ark @arkark_]

Cross-Site ETag Length Leak
https://t.co/RYofmHVh6T

I just posted the author writeup for impossible-leak in SECCON CTF 14 Quals. As far as I know, this is a new XS-Leak technique! The ETag header can become a side channel :)

[@[email protected] @SecurityMB]

@canva Ah, it's probably from the old leak: https://t.co/qnfXLTysB9

[@[email protected] @SecurityMB]

Has there been some email leak from @Canva? Just got a spam message for an email used only for Canva.

[Natalie Silvanovich @natashenka]

We launched a redesigned Project Zero website today at https://t.co/Prd8nehY7q !

To mark the occasion, we released some older posts that never quite made it out of drafts.

Enjoy!

[Google VRP (Google Bug Hunters) @GoogleVRP]

Interested in the security of AI Agents 💁🛡️?

Then you've likely heard of "prompt injection", but do you know what "task injection" is? If you're curious, check out our latest post for a description and some real-world examples we discovered.

https://t.co/pWdDGX6M0W https://t.co/P8ndgCXtH1

[Rebane @rebane2001]

my new blogpost is out!!

this one talks about a new web vulnerability class i discovered that allows for complex interactive cross-origin attacks and data exfiltration

and i've already used it to get a google docs bounty ^^

have fun <3

https://t.co/PBct6aB24W

[@[email protected] @SecurityMB]

@sephr Exploiting https://t.co/X2PmY6dUQm