All posts
Topic
Red Teaming
2 articles on red teaming.
RedCell: The Open-Source AI Agent That Runs a Penetration Test End to End
A deep dive into RedCell (github.com/martian56/redcell): open-source AI agents that plan and run a full penetration test with real tools — nmap, nuclei, Metasploit and an agent-driven browser inside a Kali container — then write the PDF/JSON/SARIF report. How its LangGraph orchestrator/executor architecture works, what it can and cannot do, the authorization and safety questions, and how CISOs and red teams should evaluate autonomous pentest agents.
September 7, 2026
Abliterated Models Explained: What Refusal-Removed LLMs Like GLM-5.3-Cybersecurity Mean for Your Threat Model
A CISO guide to abliterated models: how "abliteration" surgically removes an LLM's refusal behaviour without retraining, why refusal-removed offensive-security releases such as GLM-5.3-CYBERSECURITY-FP8 are spreading on Hugging Face, where the real risk sits (shadow AI on laptops and agents with tools), how to detect them in your environment, and a free calculator that scores the risk of a specific deployment.
September 6, 2026