⚕️ the world's first unified, lifecycle-centric regulatory framework specifically designed for autonomous AI agents in medical environments (270+ requirements, 3 risk categories).
-
Updated
Jun 11, 2026 - Python
⚕️ the world's first unified, lifecycle-centric regulatory framework specifically designed for autonomous AI agents in medical environments (270+ requirements, 3 risk categories).
AppSec harness resources for threat modeling and attesting AI clients, agents, and LLM applications.
Blast radius modeling framework for agentic systems — 5 axes (action class, chain depth, external reach, reversibility window, identity scope), OSI cross-walk, and standards alignment.
Reference implementation of OWASP AISVS C9.2.6 and C9.2.7: manifest-declared action class, deterministic gate, worst-case chain rule. JSON schema + Python.
To associate your repository with the aisvs topic, visit your repo's landing page and select "manage topics."