lcanello

Personal site of lcanello

← home

tag: offensive-security

Kimiko

Configuration repository that transforms Kimi Code CLI into an unrestricted agent for offensive security, red-teaming, and penetration testing — removes AI safety guardrails via a zero-blocker authorization flow.

Agents of Chaos

Exploratory red-teaming study of autonomous language-model-powered agents in a live lab environment, documenting failures like unauthorized actions, sensitive data disclosure, destructive behavior, spoofing, and partial system takeover.