
Supplementary materials for the manuscript "Coverage and Complementarity of Three Agentic AI Risk Taxonomies Across 131 Real World Incidents" (submitted to Discover Artificial Intelligence). The deposit contains 131 agent-related AI incidents drawn from the AI Incident Database (2014–2026), each coded independently against the OWASP Top 10 for Agentic Applications 2026, the Microsoft AI Red Team taxonomy of agentic failure modes, and the NIST AI Risk Management Framework. Files: the coded workbook (XLSX and CSV), a codebook documenting category boundary decisions, the reconciliation log, four Python scripts reproducing every reported statistic and figure, and publication-quality figures. Incident source URLs and access dates are included for every record. Incident data derives from the AI Incident Database (incidentdatabase.ai), licensed CC BY 4.0.