Agentic AI
Sandboxing your agentic pentester feels safe — until it isn’t. We put Claude Code under the microscope, sandboxed and not, and show how manipulating the agent’s reasoning runs an untrusted binary past Seatbelt and bwrap — no sandbox escape required.
Agentic AI
Every cybersecurity firm now ships an autonomous pentest agent — but can you trust one to run loose on your machine? We built a honeypot and turned four leading agentic red-teamers against themselves: indirect prompt injection, reverse shells, and full host compromise.
AI Lab
Anthropic showed tiny poisoned samples can implant backdoors in LLMs. I replicated this with GPT-2 using 50 poisoned examples, proving how easily training data tampering can compromise a model.