PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Claude Code Hacking Skills Video

josephthacker.com | research | #ai-security | #claude-code | #offensive-security | #video | #agentic-hacking
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Joseph Thacker shares a video demonstrating hacking skills built on Claude Code, showing how AI coding agents can be applied to security research workflows.
Published
Collected

Related coverage

research · portswigger.net
"The entire internet is broken": ethical hacking expert John Hammond meets James Kettle
John Hammond and James Kettle discuss the HTTP/1.1 Must Die research in a video, covering new desync attack classes, CDN compromises, and the case for moving upstream connections to HTTP/2.
research · portswigger.net
Using AI to find web app vulnerabilities: hacking expert John Hammond takes Burp AI for a spin
Security researcher John Hammond tests Burp AI in a video walkthrough, showing how it identifies subtle vulnerabilities, reduces false positives and augments testers without replacing them.
research · projectdiscovery.io
Chain-of-thought analysis of agents on offensive security tasks
# Chain-of-thought analysis of agents on offensive security tasks Sep 7, 2026 · Tarun Koyalwar Short insights from reading the chain-of-thought traces our agents left while working through...
research · vercel.com
Everything hackable will get hacked
Open-weight models that allow perform offensive research present an emerging cybersecurity challenge. But you do not need to wait for specialized models to begin defensive cybersecurity work.
research · vercel.com
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilities
Today we're releasing DeepsecBench, a benchmark that evaluates how well different models find security vulnerabilities in application code.
research · vercel.com
Security boundaries in agentic architectures
A framework for drawing security boundaries in agentic architectures. Most agents run with zero isolation between the agent and the code it generates. Learn where to draw the boundaries, from secret injection to full application sandboxing.
Back