Open-source AI Bill of Materials (AIBOM) scanner: inventories AI models, datasets, prompts, embeddings, vector DBs & RAG pipelines across code, containers & Kubernetes — with file:line evidence, load-time risk detection (poisoned pickle / Keras Lambda / unsafe torch.load) and NIST AI RMF / OWASP compliance mapping. CycloneDX · SARIF · JSON.

Jupyter notebook demonstrating some of the immense capabilities of Prisma AIRS Model Security.

Prisma AIRS AI Model Security scanning for Azure DevOps pipelines - gate builds on malicious or unsafe AI/ML models. Azure DevOps companion to model-security-pipeline-integration.

Bootable local-first AI OS with sealed runtime, model quarantine pipeline, airlock egress controls, encrypted vault, and private Tor-routed search.

Mindgard — AI red-teaming and security testing platform for LLMs and AI systems

Statically detect malicious pickle opcodes in ML model files (.pkl/.pt/.pth) without unpickling them.

AI/ML supply chain security scanner for detecting malicious payloads, unsafe deserialization, and hidden RCE inside model files like Pickle, PyTorch, and more.

Seven-stage AI artifact admission-control pipeline

AI Evaluator Pro 🛡️ is an AI security auditing tool that checks Hugging Face models for supply chain risks, unsafe formats, and author trust using OSINT + LLMs. It supports direct or discovery-based audits to detect security and integrity issues before deployment.

Protect AI — AI/ML security (Guardian, LLM Guard, Rebuff, Sightline). Acquired by Palo Alto Networks 2025.

HiddenLayer — AI/ML security platform (AISec, AIDR)

Security Lab by AccessQuint — reproducible, Docker-based, benign-canary evaluations of AI/ML security tooling. Independent, show-your-work benchmarks: model scanners, MCP agent security, and more.