LLM Agent Honeypot
Deployed vulnerable servers to catch autonomous AI hacking agents — an early warning system for AI-powered cyberattacks.
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 Top-Tier 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.