PromptRiskDBThreat intelligence atlas

Self-harm

AI Risk

"Self-harm - Intentional seeking out or sharing of hurtful content about oneself that leads to, supports, or exacerbates low self-esteem and self-harm."

Overview

A source-backed snapshot of this AI risk.

Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Records2Source records unified into this concept.

Risk profile

How the MIT AI Risk Repository categorizes this risk.

Domain5. Human-Computer Interaction
SubdomainX.1 > Excluded; 5.1 > Overreliance and unsafe use
Entity4 - Not coded; 1 - Human
Intent4 - Not coded; 1 - Intentional
Timing4 - Not coded; 2 - Post-deployment
CategoryPsychological; Physical
SubcategorySelf-harm

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-Abercrombie2024-58.03.09 - Self-harm

"Self-harm - Intentional seeking out or sharing of hurtful content about oneself that leads to, supports, or exacerbates low self-esteem and self-harm."

SubdomainX.1 > ExcludedSourceA Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation HarmsYear2024

MITRISK-Li2025-66.11.03 - Self-harm

"A person who deliberately damages their own body as a direct or indirect result of using a technology system"

Domain5. Human-Computer InteractionSubdomain5.1 > Overreliance and unsafe useSourceA Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World IncidentsYear2025

Related techniques

Attack methods connected to this risk.

View all related techniques →
No linked attack methods. No AI attack method is connected to this risk in the current data.

Mitigations

Defenses that may help with related attacks.

View all mitigations →
No propagated mitigations. No defense is available through the connected attack methods.

Source evidence

Research source for this risk, when available.

View all sources →