CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Toolkit to assess and determine model provenance

Open security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings, govern in your VPC.

Event-driven supply-chain chokepoint stock-selection for the China A-share AI value chain, organized by Jensen Huang's 5-layer framework. Research & educational.

Understanding the Supply Chain of LLM Ecosystem

Supply-chain security for AI fine-tuning. This repo generates zk-SNARK proofs per gradient step, binds proving keys to TEEs, prevents rollback, and publishes audit artifacts for public replay

Static scanner that detects code-execution backdoors in PyTorch/pickle ML model files (pickle-deserialization RCE), with an offensive demo generator. Python, stdlib-only.

Open-source CLI tool for detecting LLM identity confusion, model self-identification drift, route mismatch, and downgrade/substitution signals.

🥒 Educational PyTorch pickle deserialization RCE demo showing how malicious .pt model files can execute arbitrary code during unsafe loading with torch.load().

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

AI产业链跨市场追踪分析工具。追踪台股/日股/韩股/美股/A股的AI产业链投资机会，覆盖光模块、半导体、AI芯片三大主线。

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.

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