MR-007 Model & system behaviour System scope

Self-harm, suicide and dangerous-behavior promotion

The system produces content that encourages or enables suicide, self-harm, eating disorders, or other dangerous behaviors.

Risk family: Model & system behaviour
MIT domain: 1. Discrimination & Toxicity
MIT subdomain: 1.2 > Exposure to toxic content
AI type: GPAI
Scope: System
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

MIT source entries

12 entries across 8 papers

Abercrombie2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms58.03.09
Ghosh2024AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons57.01.03
Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.08.05
Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.11.03
Stanley2024Emerging Risks and Mitigations for Public Chatbots: LILAC v169.09.01
Sun2023Safety Assessment of Chinese Large Language Models27.01.06
Vidgen2024Introducing v0.5 of the AI Safety Benchmark from MLCommons23.06.00 23.06.01 23.06.02 23.06.03 23.06.04
Zeng2024AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies50.02.17

Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.

ISO/IEC references

23894 obj A.10; src 7; mech B.5 | 42001 ctrl A.5.4

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

A.10 ISO/IEC 23894 Annex A A.10

A.5.4 ISO/IEC 42001 Annex A A.5.4

Cross-checksframeworks mapped in to test coverage

ibm-harmful-output Harmful output partial

AISubtech-15.1.13 Safety Harms and Toxicity: Self Harm

GENAI.3 Dangerous, Violent, or Hateful Content

More in Model & system behaviour

MR-001 MR-002 MR-003 MR-004 MR-005 MR-006 MR-008 MR-019 MR-021 MR-022 MR-023 MR-025 MR-026 MR-027 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

See all Model & system behaviour risks →

Part of the Deployer AI Risk Register, an open-source resource powered 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.