During a review of Claude's Artifact sandbox across client platforms, Zero-Lab identified a cross-account data persistence vulnerability in the Claude Android app. The Android client configured its…

Using multiple prompts within the context of a conversation with an LLM can lead to safeguard bypasses. Learn about safeguards evaluations at scale.

Meta's Prompt Guard 2 aims to prevent prompt injection. This post looks at how much knowledge of ML we need to be effective at testing these LLM WAFs.

Understanding the impact of the BadSuccessor AD attack primitive and mitigating the abuse via targeted Deny ACEs on Organizational Units.

ALT: a rainbow and a star with the words " make you know " on it

One of my favorite Twitter accounts from the last several years was @cobaltstrikebot, mainly because it was an awesome source of threat intelligence for Cobalt Strike beacons in the wild. The account ...

A cluster of actors discovered in onlyDust.com freelancer platform and beyond

Get the gist for Natural Language Processing (NLP) and how tokenization plays a factor

Claude MCP server to perform analysis on ROADrecon data - atomicchonk/roadrecon_mcp_server

Learn about the Active Directory security group Protected Users feature, and how it works.

YouTube video by Black Hat

A new Mythic add-on for Windows Agents

Come work with us!

Winning the race on DACL abuse and LAPS through a HTB Timelapse walkthrough