Jürgen Cito

Autonomous AI agents in offensive security blur the lines of accountability, making it easier for malicious actors to exploit their capabilities without clear attribution of responsibility.

Minification techniques can cut token usage by 42% in state-in-context agents, but at the cost of a notable drop in resolution rate.

Local LLMs can now rival cloud-based giants like GPT-4o in Linux privilege escalation tasks, thanks to targeted system-level and prompting interventions.

LLMs might be surprisingly capable penetration testers for enterprise networks, and this report provides the recipe to reproduce the original findings.