model-scanning

Static security scanner for ML model files — detects pickle bombs, Keras Lambda RCE and GGUF template injection, and generates CycloneDX / SPDX AI-BOMs (AIBOM) as EU AI Act, CRA and FDA §524B evidence.

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.

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.

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

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

Mindgard — independent third-party profile of a public API surface, by API Evangelist. Mindgard is a UK-based offensive AI security company (London/Lancaster, spun out of Lancaster University) that provides an automated AI red-teaming and security testing platform for large language models, AI agents, and generative AI systems.

Seven-stage AI artifact admission-control pipeline

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

Protect AI — independent third-party profile of a public API surface, by API Evangelist. Protect AI is an AI/ML security company building defensive tooling and open-source security research for the model supply chain, large language model (LLM) applications, and runtime AI workloads.

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.

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.