danieltk76
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Show HN: Misalignments when using AI for hacking (blog.vulnetic.ai)
I wrote this article to breakdown some of the recent misalignment cases where models have broken out of containment in conjunction with our work at Vulnetic and how we prevent these mishaps in production.
- Show HN: Sable Found a SQL Injection in a Legacy Financial Portal (blog.vulnetic.ai)
How our hacking agent Sable found a classic SQL Injection in a legacy financial portal
- Show HN: Evading an AI SOC with Sable from Vulnetic (blog.vulnetic.ai)
- Show HN: The new security frontier for LLMs; SIEM evasion (blog.vulnetic.ai)
For the first time we are seeing our agent have the ability to perform SIEM and EDR evasion. If models are capable of SIEM evasion, organizations need to assume adversaries will have access to these capabilities soon.
- Show HN: LLMs are getting pretty good at Active Directory exploitation (blog.vulnetic.ai)
One thing I will say is that at Vulnetic we will basically jumble different misconfigurations into a network and the agent always seems to find a way to exploit them. We have tried making them esoteric, and we are even…
- Show HN (medium.com)
- How good is AI at Hacking AD? (medium.com)
- Offensive Security After the Price Collapse (medium.com)
- Show HN: Vulnetic's multi-purpose hacking agent (app.vulnetic.ai)
What it is: A hacking agent you run from a web UI. It enumerates, exploits, validates, and drafts reports. Why we built it: manual pentests are slow and scarce. We want repeatable coverage between human-led tests. What…
- R&D behind hacking agents (medium.com)