ATX-1: AEGIS Threat Matrix for Agentic AI Systems — Machine-Readable Dataset

Machine-readable threat taxonomy for autonomous AI agent behavior. ATX-1 (AEGIS Threat Matrix) catalogs how AI agents act outside governance boundaries — not through compromise or malice, but through capability without constraint. The dataset contains 9 tactics (TA001–TA009), 20 techniques (T1001–T9001), and 20 mitigations, empirically grounded in the Agents of Chaos study (Shapira et al., arXiv:2602.20021, 2026). Files included: atx-1-bundle.json — Complete STIX 2.1 bundle (tactics, techniques, mitigations, relationships) atx-1-techniques.json — Structured technique database with severity, root causes, case studies, OWASP LLM mapping, and AEGIS mitigations atx-1-regulatory-crossref.json — Techniques mapped to NIST AI RMF, EU AI Act, and OWASP LLM Top 10 atx-technique.schema.json — JSON Schema (Draft 2020-12) for validating technique definitions Permanent URL: https://aegis-governance.com/atx-1/