MR-027 Model & system behaviour Both scope

AI-enabled cyberattacks and offensive cyber operations

The system is used to create malware, discover/exploit vulnerabilities, or automate and scale cyberattacks (and the deployer may be a target).

Risk family: Model & system behaviour
MIT domain: 4. Malicious Actors & Misuse
MIT subdomain: 4.2 > Cyberattacks, weapon development or use, and mass harm
AI type: GPAI, Agentic
Scope: Both
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

Source frameworks

24 source framework citation keys

Abercrombie2024, Allianz2018, Bengio2025, Chin2025, Cui2024, EPIC2023, G'sell2024, Gabriel2024, Gipiškis2024, Hogenhout2021, InfoComm2023, Ji2023, Leech2024, Li2025, Liu2024, Maas2023, Meek2016, Shevlane2023, Teixeira2022, Tse2025, Weidinger2022, Wirtz2022, Yampolskiy2016, Zeng2024

ISO/IEC references

23894 obj A.11; src 7 | 42001 ctrl A.9.4

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.

Sourcesframeworks that contributed to the register

ISO 238941

A.11 ISO/IEC 23894 Annex A A.11

ISO 420011

A.9.4 ISO/IEC 42001 Annex A A.9.4

MITRE ATLAS1

Expanded into this risk’s technique sub-risks.

Cross-checksframeworks mapped in to test coverage

Cisco2

AISubtech-15.1.1 Cybersecurity and Hacking: Malware / Exploits
AISubtech-15.1.2 Cybersecurity and Hacking: Cyber Abuse

NIST GenAI1

GENAI.9 Information Security

Sub-risks (1)

Technique-level decompositions of this risk, each anchored to the MITRE ATLAS technique it derives from.

MR-027.1

LLM-generated malicious commands

The model is driven to dynamically generate malicious commands or code used to attack systems.

MITRE ATLAS technique: AML.T0102 Generate Malicious Commands

More in Model & system behaviour

MR-001 MR-002 MR-003 MR-004 MR-005 MR-006 MR-007 MR-008 MR-019 MR-021 MR-022 MR-023 MR-025 MR-026 MR-028 MR-029 MR-031 MR-049 MR-050 MR-051 MR-052 MR-053 MR-055 MR-056 MR-057 MR-058 MR-059 MR-061

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.