Hi, I'm Sergei, building AI security tools at SCADA StrangeLove
I'm Sergei Gordeichik, founder of SCADA StrangeLove. Our work lives mostly on GitHub, where we have 56 repositories. The ones I'm proudest of are awesome-ai-security-tools, a curated list of AI security tools, rust-in-peace and reproof, 0/1-day vulns research harness, and asamm, an OWASP SAMM extension for AI-driven development.
Right now I'm exploring agent-assisted vulnerability research: independent discovery, skeptical triage, verification. Playing with agents alignment with Selective Permeability, a behavioral-security metric for LLM advisors.
What I'd love from this community: an intro to anyone securing AI agents in production, or investors who follow AI security, so I can compare notes on what teams actually need.
Introductions
