HackerTrans
TopNewTrendsCommentsPastAskShowJobs

danieltk76

6 karmajoined 2 anni fa

Submissions

[untitled]

1 points·by danieltk76·2 mesi fa·0 comments

Show HN: Sable Found a SQL Injection in a Legacy Financial Portal

blog.vulnetic.ai
1 points·by danieltk76·3 mesi fa·0 comments

Show HN: Evading an AI SOC with Sable from Vulnetic

blog.vulnetic.ai
1 points·by danieltk76·3 mesi fa·0 comments

Show HN: The new security frontier for LLMs; SIEM evasion

blog.vulnetic.ai
2 points·by danieltk76·4 mesi fa·0 comments

Show HN: LLMs are getting pretty good at Active Directory exploitation

blog.vulnetic.ai
3 points·by danieltk76·5 mesi fa·0 comments

Show HN

medium.com
2 points·by danieltk76·6 mesi fa·0 comments

Show HN: AI attacking AI? Vulnetic offensive security agent compromising models

blog.vulnetic.ai
2 points·by danieltk76·6 mesi fa·0 comments

How good is AI at Hacking AD?

medium.com
1 points·by danieltk76·8 mesi fa·0 comments

Offensive Security After the Price Collapse

medium.com
1 points·by danieltk76·10 mesi fa·0 comments

Show HN: Vulnetic's multi-purpose hacking agent

app.vulnetic.ai
1 points·by danieltk76·10 mesi fa·0 comments

comments

danieltk76
·5 giorni fa·discuss
vulnetic.ai is designed for this! Check us out!
danieltk76
·25 giorni fa·discuss
i remember using continue before cursor lmaoo so like early 2023?
danieltk76
·mese scorso·discuss
well well well....vulnetic.ai
danieltk76
·2 mesi fa·discuss
gotta love how vulnerable those are lol nice
danieltk76
·2 mesi fa·discuss
OT does not need to be on the open internet for this to matter. Models can infer during exploitation by performing the same reconnaissance steps used in other offensive contexts, then filling in the gaps from observed behavior. We have seen this by testing our own agent against strange environments with varied defenses it likely had not encountered before.

The training set matters less than many people assume. The model’s raw reasoning ability, tool use, and ability to adapt from feedback are the bigger issue. If a model were only repeating its training data, it would not be generalizing, it would just be overfit to its dataset.
danieltk76
·2 mesi fa·discuss
who cheats in war thunder...
danieltk76
·2 mesi fa·discuss
100% lmao
danieltk76
·2 mesi fa·discuss
GTFOBins has been around for a while. a useful resource pre AI
danieltk76
·2 mesi fa·discuss
Hey! absolutely it exists. We sell to large companies and penetration testing firms and assessments from our agent cost 1/50th the cost of a normal pentest. happy to chat! https://vulnetic.ai
danieltk76
·3 mesi fa·discuss
There are never ending ways to make agents better at hacking. Defense is clearly behind. At my startup we are constantly coming up with new defensive measures to put our hacking agent Sable against, and I've determined that you basically need to be air gapped in the future for a chance of survival. A SOC of AI agents can't keep up with 1 AI hacker on a network that is even remotely stealthy. it is a disaster. wrote an article about it: https://blog.vulnetic.ai/evading-an-ai-soc-with-sable-from-v...
danieltk76
·4 mesi fa·discuss
Super fun running these tests. More to come!
danieltk76
·5 mesi fa·discuss
We use Cardboard at Vulnetic and it is an incredible product. The founders are easily accessible, and it has definitely made it easier to film feature update videos. I can't recommend them enough.
danieltk76
·7 mesi fa·discuss
and here begins the downfall of Warner Bros.
danieltk76
·8 mesi fa·discuss
At Vulnetic ai we deal with this by having a separate validator agent attack the vulnerability reported using a novel perspective separate of the hacking agent.