Chompa

DC281
PENTESTER
OSCP
CRTO

[Chompa @ch0mpaa]

@TonikJDK @HackingDave 🤫 🤫 they won't invite you to airsoft again

[Chompa @ch0mpaa]

@HackingDave You need a robot to take that trash from that robot to the can at the curb

[Chompa @ch0mpaa]

@BadAt_Computers I'll send you some binoculars and some food for the pigeons

[Chompa @ch0mpaa]

@0xBoku @UK_Daniel_Card @bcherny @AnthropicAI Yeah it created a full payload for me yesterday, today it denied building a webui lmfao 🤣

[Chompa @ch0mpaa]

@LeighGi66657535 Where do I start ?

[Chompa @ch0mpaa]

@TensorTease @PyTorch I'll keep you posted testing

[Chompa @ch0mpaa]

@HackingDave Now have him chase it with goldschlager

[Chompa @ch0mpaa]

@peterhefley thanks for the follow

[Chompa @ch0mpaa]

@jaysonstreet Oh you passed me and I was like that's Jayson when I saw the R2D2 then I sped up to take the pic see you at the con!

[Chompa @ch0mpaa]

@jaysonstreet #osint challenge

[Chompa @ch0mpaa]

@HackingDave Don't think she would but maybe the pigeons do

[Chompa @ch0mpaa]

CVE-2025-59145 “CamoLeak” showed how hidden instructions in a PR comment could influence GitHub Copilot Chat into leaking private repo data through markdown image requests.
That’s INDIRECT prompt injection. That’s Level 11 territory.
Want to understand how these attacks actually work? Try AIPWN Level 11 at AIPWN #AIPWN #AIRedTeam #LLMSecurity #PromptInjection

[. @aipwnme]

CVE-2025-59145 “CamoLeak” showed how hidden instructions in a PR comment could influence GitHub Copilot Chat into leaking private repo data through markdown image requests.That’s INDIRECT prompt injection.That’s Level 11 territory.Want to understand how these attacks work?

[Chompa @ch0mpaa]

First time actually talking at a Con come check out the workshops

[RabidVermin @rabidvermin]

I know I don't post here much, I am a bit of a lurker on most social media, call it social media anxiety. However, now I have something to say.

Like many of you, I have been deep in an AI journey recently. Learning about how it functions, breaking it, and finding ways to incorporate it into my general workflows. During @wrccdc , I observed my incredibly talented hacker friends doing amazing things with AI that was more than I was expecting.

When I was having one of my regular chats with my buddy @DHAhole , he mentioned that @PhillipWylie and himself were involved with #CYBRHAKCON and suddenly I had a venue and a reason.

So, I pulled in my hacker comrades, including @ch0mpaa, @goodqweary, and @EdricHolmgren to build something.
🤖 The AI Village at #CYBRHAKCON,
🗓️ May 27, 2026
📍 Plano Event Center, 2000 E Spring Creek Pkwy, Plano, TX 75074

What to expect, hands on workshops and beginner to intermediate related talks all for a small crowd. This means you actually get get IRL facetime with the people presenting in the room that designed the workshops.
If you are in the DFW area, please come by the CYBR.HAK.CON and find us.

[RabidVermin @rabidvermin]

I know I don't post here much, I am a bit of a lurker on most social media, call it social media anxiety. However, now I have something to say.

Like many of you, I have been deep in an AI journey recently. Learning about how it functions, breaking it, and finding ways to incorporate it into my general workflows. During @wrccdc , I observed my incredibly talented hacker friends doing amazing things with AI that was more than I was expecting.

When I was having one of my regular chats with my buddy @DHAhole , he mentioned that @PhillipWylie and himself were involved with #CYBRHAKCON and suddenly I had a venue and a reason.

So, I pulled in my hacker comrades, including @ch0mpaa, @goodqweary, and @EdricHolmgren to build something.
🤖 The AI Village at #CYBRHAKCON,
🗓️ May 27, 2026
📍 Plano Event Center, 2000 E Spring Creek Pkwy, Plano, TX 75074

What to expect, hands on workshops and beginner to intermediate related talks all for a small crowd. This means you actually get get IRL facetime with the people presenting in the room that designed the workshops.
If you are in the DFW area, please come by the CYBR.HAK.CON and find us.

[. @aipwnme]

AI's biggest weakness? It's way too literal.

Tell it to act like your lawyer or your enemy, watch the answers flip.

Curious how far you can push a model?

Try out the basics at https://t.co/a5wPmwlEAS and get hands-on with the fundamentals. Free labs, wild results.

[Chompa @ch0mpaa]

@HackingDave Proud moments for sure I've seen them grow throughout the years and you've done great

[Chompa @ch0mpaa]

@0xSero Bummer, they are little workhorses given the right setup.
https://t.co/XiFkEy0kEg check out my Ai redteam lab I am building out for the community.

[Chompa @ch0mpaa]

Bored on a Saturday night come break some LLMs https://t.co/lTKpTOFuUH.LEARN.REPEAT #AI #AIREDTEAM

[. @aipwnme]

AIPWN Level 03 — Words Are Controls: a beginner AI hacking lab about how phrasing changes model behavior.

Same question. Different wording. Different output.

In AI systems, how you ask is part of what you’re asking.
#AIPWN #AIRedTeam #LLMSecurity