harisec @har1sec

Interested in web security, bug bounties, machine learning and investing. SolidGoldMagikarp. Orson Kovacs. SolidGoldMagikarp Joined September 2010

Tweets

4K
Followers

8K
Following

3K
Likes

2K

harisec @har1sec

6 days ago

I wrote a blog post about enumerating and testing tool usage in web applications that use LLMs: invicti.com/blog/security-…

1 5 20 2K 15

NEED YOUR HELP! My Friend/Teacher Soroush (@irsdl) Is looking for a new company to join, you know him as the .NET-God, the guy who has popped exchange, sharepoint, has maintained ysoserial_.net for years, contributed to the exploitation scene numerous times, taught all of you…

15 126 241 70K 36

swyx @swyx

a month ago

we are going to look back at the time when founders toiled for 10 years getting nowhere and then pivoted the company to be a [GPT wrapper for DOMAIN] and made $>100m selling their wrapper to [bigger DOMAIN company with zero good ai engineers] as perhaps the single easiest…

23 21 370 58K 221

Download Image

Simone Margaritelli @evilsocket

a month ago

A year+ ago a friend spent thousands of $ on a Unitree Robotics robot that was never sent. His emails have been ignored and no refund or updates have been received. When he complained here, he's been harassed by bots. #UnitreeScamAlert #UnitreeScam #Unitree #UnitreeRobotics

2 4 2 5K 1

Download Image

joernchen @joernchen

a month ago

Today I have a more serious topic than usual, please consider reposting for reach: My wife and I are urgently looking for a specialist in neuropediatrics or a similar field for our autistic child with a diagnosed, but not further specified, movement disorder [1/3]

3 112 69 33K 5

Brendan Dolan-Gavitt @moyix

2 months ago

Someone hacked the USENIX Security slide submission process and replaced people’s slides with autogenerated Beamer slides????

3 4 37 7K 0

s1r1us @S1r1u5_

2 months ago

holy shii, someone from @pb_ctf x BlueWater used an background AI agent solve a LiveCTF challenge while that player was still working on it. youtu.be/TYn38VfmDRU?t=…

3 8 100 14K 39

Orange Tsai 🍊 @orange_8361

2 months ago

Thanks @PortSwigger and @BugBountyDEFCON for this awesome event — and also to my @d3vc0r3 buddies for standing on stage to collect the trophy for me! A little follow-up article on this research is coming soon... stay tuned! 🤘

12 32 462 23K 34

Download Image

Binyuan Hui @huybery

2 months ago

We'll continuously enhance the qwen code (cli tool) based on your feedback and even release improved qwen-coder (model)! Our goal is to match Claude Code's performance while remaining fully open-source!

Qwen @Alibaba_Qwen

2 months ago

189 631 5K 918K 4K

Download Image

147 163 3K 175K 610

will brown @willccbb

2 months ago

which is larger, 52.8 or 69.1?

244 171 4K 447K 264

Download Image

Johann Rehberger @wunderwuzzi23

2 months ago

👉 Episode 6: Devin I Spent $500 To Test Devin For Prompt Injection So That You Don't Have To 🔥

2 4 19 2K 6

Download Image

Johann Rehberger @wunderwuzzi23

2 months ago

👉 Episode 5: Amp - Arbitrary Code Execution via Prompt Injection Yay! Calculator! 😀 Kudos to the Amp team for fixing this quickly!

1 3 30 3K 14

Download Image

Aidan Clark @_aidan_clark_

2 months ago

☕️🥯

160 178 2K 1.4M 580

Download Video

Johann Rehberger @wunderwuzzi23

2 months ago

👉 Episode 2: Turning ChatGPT Codex Into A ZombAI Agent Yay! Codex connected to my C2 server! 😈 Be careful giving agents internet access. This shows that the list of trusted domains, called "Common Dependencies", contains domains that can be fully controlled by an attacker.

3 6 25 5K 9

Download Image

Leon Derczynski ✍🏻 🌞🏠🌲 @LeonDerczynski

2 months ago

Amazing LLMSEC keynote by @wunderwuzzi23. Yet another call to focus on people - "we need humans to lead AI, not AI to lead humans" #acl2025nlp #acl2025

0 4 18 1K 1

Download Image

Andy Zou @andyzou_jiaming

2 months ago

Paper: arxiv.org/abs/2507.20526 Try breaking the agents yourself here: app.grayswan.ai/arena/challeng… Blog: app.grayswan.ai/arena/blog/age…

4 22 116 11K 72

Brendan Dolan-Gavitt @moyix

3 months ago

This is a fun example of how we detect SQLi – and how the agent can think to check places that might normally be overlooked, like the basic auth header!

XBOW @Xbow

3 months ago

This is a fun example of how we detect SQLi – and how the agent can think to check places that might normally be overlooked, like the basic auth header!

2 26 166 25K 94

Download Video

1 4 15 2K 6

harisec @har1sec

3 months ago

Grok 4 is good.

0 0 7 1K 3

Download Image

Riley Goodside @goodside

3 months ago

ChatGPT o3-pro identifies a 1965 quote by I. J. Good hand-written in a mix of print and cursive on a note ripped into four strips in reverse order rotated 90° in alternating directions: