Testing & Red Teaming
Attack your AI systems before someone else does — from LLM pentests and Agent Skill reviews to continuous AI Red Teaming.
Agentic AI Security: securing & governing AI systems
LLM and agentic AI pentesting, Prompt Injection, OWASP LLM Top 10, MAESTRO Threat Modeling and AI governance: how to test AI systems, make them transparent and operate them in full regulatory compliance.
Agentic AI systems act instead of merely answering — with tool access, memory and their own decisions. This creates attack surfaces that classic security testing does not cover: Prompt Injection, Memory Poisoning, tool misuse and compromised Agent Skills. These knowledge pages combine offensive testing (OWASP LLM Top 10, agentic threats), engineering transparency (AI-SBOM, automated Threat Modeling) and governance (EU AI Act, ISO/IEC 42001) into one end-to-end approach.
Topics & knowledge pages
Each topic leads to a dedicated knowledge page with deep dives, practical guides and the matching services.
Engineering & transparency
Systematically model threats and make the supply chain of AI systems visible — all the way to the AI-BOM.
Governance & threat landscape
EU AI Act, ISO/IEC 42001 and the current AI threat landscape — know your obligations, assess risks realistically.
Deep Dives
In-depth knowledge pages on the topics that currently raise the most questions — with verified sources and concrete measures.
MCP Security
The Model Context Protocol connects AI applications with tools, data, and systems – creating a new attack surface in the process. We put the current guidance from the NSA, OWASP, and Wiz into context and show how you can secure MCP servers and clients.
View knowledge pageOWASP Agentic Top 10
The ten key security risks of autonomous AI agents – from Agent Goal Hijack to Rogue Agents – based on the official OWASP publication (version 2026, December 2025).
View knowledge pageZero Trust for AI Agents
Autonomous AI agents act with legitimately granted privileges at machine speed. Zero Trust transfers proven principles — verify instead of trust, Least Privilege, assume breach — to agentic systems.
View knowledge pageAI Security Frameworks
OWASP, MITRE ATLAS, and NIST AI RMF look at AI security from three different perspectives. An overview of what each framework stands for — and how, in combination, they form a viable protection concept.
View knowledge pageWhitepapers for download
Each whitepaper has its own page with details and a direct download form.
Using AI? Then test it, too.
In an initial consultation, we clarify which of your AI systems should be tested — and how testing, transparency and governance work together.