onsite
Thesis: Hack Yourself First: Autonomous LLM Agents for Continuous Penetration Testing
AI Engineer
A thesis position in Sundsvall where the student builds and evaluates an autonomous LLM agent that runs continuous penetration tests inside a deliberately vulnerable lab network — performing reconnaissance, exploitation and reporting — using tools such as MCP, Linux and Nmap, while assessing reliability and safety of the agent's findings.
About the role
High Level Description
Insecure systems are everywhere. What matters is who finds the exploit first. Internal networks, such as an office LAN, are often assumed to be secure, but a single rogue or insecure IoT device, such as a smart TV, can give an attacker a way in. Penetration testing means trying to break into your own systems, with permission, to find security issues before an attacker does. It needs skilled people, so it is often done only now and then, while the systems keep changing.
Large Language Model (LLM) agents can now use tools and solve tasks in several steps. They are starting to be used for attacks, but how useful they are for defence is not yet well studied.
This thesis will investigate how an LLM agent can secure a network by acting as an attacker. The agent finds issues, investigates them and sends a report to the person responsible for the security posture.
Project
Skills
claude codeclicybersecurityfine tuninggdprgithubgithub copilotlinuxllmmcpnmapowasppenetration testing