Goal / Research Questions:
- What are the risks of external tools and skills?
- How can potentially unsafe or unreliable components be identified?
- How can secure integration mechanisms be designed?
Please contact Andreas Ekelhart.
The following contains currently open thesis topics in our areas of research. If you are interested in a topic or have a thesis idea of your own that might fit our research interests, please contact us directly.
Skill and MCP Security Analysis in Agent Systems
Agent systems rely on external tools and skills (e.g., APIs, plugins, MCP servers). This topic investigates the implications of integrating such components into AI-based systems.