LLM Agent Honeypot
Open-source honeypot to monitor autonomous AI hacking agents in the wild. First documented evidence of AI agents attacking real infrastructure.
AI Security Researcher
Reworr R.
Researching novel threats at the intersection of AI and cybersecurity
(autonomous hacking, large-scale OSINT, loss of control).
Background in offensive security (penetration testing / vulnerability research).
Currently: Palisade Research
Featured Work
AI Hacking Cable
Demonstrating operational feasibility of autonomous AI in post-exploitation. The agent conducts reconnaissance, exfiltrates data, spreads laterally via USB—without human intervention.
GPT-5 at CTFs
Frontier AI is as good at hacking as it is at math olympiads. GPT-5 finished 25th at elite CTFs—between world's #3 and #7 ranked teams, outperforming 93% of humans.