About Us
Manuel López & Pablo Plaza
Red Team & AI Security Researchers
Engineering & Research
Operational Background
Computer Engineers with experience executing Red Team operations, Pentesting, and adversary simulation. Consolidated technical track record in CTF competitions and traditional offensive security.
AI Engineering and Cybersecurity
Currently leading the design and development of next-generation cybersecurity tools. Our work focuses on implementing Agentic AI and LLMs to automate defensive workflows (detection, triage, and incident prioritization) and offensive operations.
Research and Development Areas
Tool Development (AI-Driven Security)
Design and programming of AI-assisted security architectures. Implementation of Agentic AI systems for operational assistance, improved threat detection capabilities, and context-based alert prioritization algorithms.
Adversarial Machine Learning (Offensive AI)
Security auditing of AI models. Research on specific attack vectors against LLMs: Prompt Injection, Jailbreaking, guardrail evasion, model extraction, and Data Poisoning.
Security Operations (SecOps)
Maintaining classic offensive capabilities (Red Teaming) while integrating advanced automation for scaling and persistence.