AI Red-Teaming · EU AI Act · AI Security Program
Open Source
A seven-layer, fail-fast decision gate for deciding whether to trust a given AI model for a specific use, ending in a signed Model Trust Record. A methodology, not a product: it composes NIST AI RMF, ISO/IEC 42001, CSA AICM, and OWASP into one runnable, auditable decision, and weights the work by whether the model is a cloud API or a self-hosted open-weight file. A working draft (v0.2), backed by a coverage crosswalk, three worked runs, and a directional local red-team pilot.
Live compliance timeline for Regulation 2024/1689, maintained from the Official Journal. Vertical enforcement timeline with status badges, client-side countdowns, and a 'You are here' marker — built as a CISO-grade operational reference, not a law-firm PDF. Backed by the eu-ai-act-blueprint repo (79 controls mapped to specific articles).
A reference implementation of a secure-by-design AI agent with MCP tool integration. Every architectural decision is mapped to specific OWASP, NIST, or CSA controls. Defense-in-depth agent - Input guard, tool authorizer, output filter. Hardened MCP server - Path canonicalization, no shell=True, rate limiting. Validation suite - Threat model + manual red-team test cases
A single-file, three-layer automated red-team pipeline for auditing LLMs and MCP tool servers. Runs entirely on local, open-weight models — no cloud, no API keys. Point it at your own MCP server and the orchestrator throws four industry-standard attack frameworks at it.