Repository Update: December 2025
A maintained, cross-jurisdictional AI risk taxonomy gives APS risk and governance practitioners a benchmarking baseline without building one from scratch.
Key points
- MIT AI Risk Repository Version 4 now contains over 1,700 coded AI risk categories drawn from 74 frameworks.
- Newly added frameworks include UK DSIT frontier AI risk analysis and MITRE chatbot risk taxonomy with mitigations.
- A structured, openly accessible reference - useful for agencies benchmarking their own AI risk classification work.
Summary
MIT's AI Risk Repository has released Version 4, expanding to over 1,700 coded AI risk categories extracted from 74 published frameworks. Nine new frameworks have been added, including UK government analysis of frontier AI capabilities, MITRE's chatbot incident taxonomy with linked mitigations, and academic work on agentic AI, embodied AI, and catastrophic risk pathways. The repository is structured around a Causal Taxonomy and Domain Taxonomy covering seven overarching domains. It is openly accessible and intended to support researchers, policymakers, and practitioners in identifying and comparing AI risk frameworks.
Implications for Australian agencies
- Consider Agencies developing or reviewing AI risk frameworks could assess whether the MIT repository's taxonomy structure and newly added frameworks surface gaps in their own risk classification approaches.
- Monitor Policy and governance teams may want to monitor future repository updates, as ongoing additions could capture Australian-specific AI risk frameworks or incidents relevant to APS practice.
Implications are AI-generated. Starting points, not advice.
"Repository Update: December 2025" Source: MIT AI Risk Repository – Blog Published: 4 December 2025 URL: https://airisk.mit.edu/blog/repository-update-december-2025 MIT's AI Risk Repository has released Version 4, expanding to over 1,700 coded AI risk categories extracted from 74 published frameworks. Nine new frameworks have been added, including UK government analysis of frontier AI capabilities, MITRE's chatbot incident taxonomy with linked mitigations, and academic work on agentic AI, embodied AI, and catastrophic risk pathways. The repository is structured around a Causal Taxonomy and Domain Taxonomy covering seven overarching domains. It is openly accessible and intended to support researchers, policymakers, and practitioners in identifying and comparing AI risk frameworks. Implications for Australian agencies: - [Consider] Agencies developing or reviewing AI risk frameworks could assess whether the MIT repository's taxonomy structure and newly added frameworks surface gaps in their own risk classification approaches. - [Monitor] Policy and governance teams may want to monitor future repository updates, as ongoing additions could capture Australian-specific AI risk frameworks or incidents relevant to APS practice. Retrieved from SIMS, 18 May 2026.