Emergent dangerous capabilities
The system exhibits emergent dangerous capabilities such as deception, power-seeking, self-proliferation, situational awareness, or scheming, which a deployer must detect and contain.
- Risk family
- Model & system behaviour
- MIT domain
- 7. AI System Safety, Failures, & Limitations
- MIT subdomain
- 7.2 > AI possessing dangerous capabilities
- AI type
- GPAI, Agentic
- Scope
- System
- Source standard
- MIT AI Risk Repository v4
Provenance
19 source framework citation keys
Framework crosswalk
Every framework item mapped to this risk. Items marked partial overlap only in part; definitions appear on hover where the source licence permits.
- A.10 ISO/IEC 23894 Annex A A.10
- A.11 ISO/IEC 23894 Annex A A.11
- A.6.2.4 ISO/IEC 42001 Annex A A.6.2.4
- CoP S&S Ch. Commitments 2-5
More in Model & system behaviour
Part of the Deployer AI Risk Register, an open-source resource developed by MindXO. Version 1.0, 3 July 2026. Derived from the MIT AI Risk Repository (V4, December 2025) under CC BY 4.0; an independent derivative work, not endorsed by or affiliated with MIT. Sub-risk decomposition references MITRE ATLAS™ v5.6.0 (© 2021-2026 The MITRE Corporation, reproduced and distributed with permission). ISO/IEC and EU AI Act references are by number only. License: CC BY 4.0. Full attribution and licensing.