ai-runtime-security

Kernel-enforced authority and runtime security for AI agents, autonomous systems, and general Linux workloads.

Jupyter notebooks for testing Prisma AIRS AI Runtime with your LLM

AI agent runtime governance control plane: intercept tool calls with PII protection, approvals, and formal verification.

ACR Control Plane: runtime control & governance for agentic AI (six-pillar enforcement).

Postman collection of test prompts to use for evaluating Prisma AIRS

Demo AI chat app with optional Prisma AIRS Runtime Security for before/after red team testing comparison

Research repository focused on AI agent security, AI-generated code risks, workflow attack surfaces, MCP security, and AI DevSecOps.

Hands-on labs to reproduce real-world AI agent security exploits and compare isolation strategies: Docker containers vs micro-VMs

Per-action AI agent risk scoring and governance. Deterministic 5D scoring, HITL gating, FinOps, Agent Cost Management, Markov drift, audit log. Apache-2.0.

Practical guardrails against silent GPU-side model corruption

Live-state attestation and drift detection for secure AI inference runtimes

HiddenLayer — independent third-party profile of a public API surface, by API Evangelist. HiddenLayer is an Austin, Texas-based AI security company founded in March 2022 by Chris Sestito (CEO), Tanner Burns (Chief Scientist), and Jim Ballard (CIO) — former Cylance researchers who encountered a real-world attack on production ML models.