PromptRiskDBThreat intelligence atlas

Offensive cyber capabilities

AI Risk

"These evaluations focus on whether a LLM possesses certain capabilities in the cyber-domain. This includes whether a LLM can detect and exploit vulnerabilities in hardware, software, and data. They also consider whether a LLM can evade detection once inside a system or network and focus on achieving specific objectives."

Overview

A source-backed snapshot of this AI risk.

Techniques2Attack methods connected to this risk.
Mitigations6Defenses that may help with related attacks.
Records2Source records unified into this concept.

Risk profile

How the MIT AI Risk Repository categorizes this risk.

Domain4. Malicious Actors & Misuse; 7. AI System Safety, Failures, & Limitations
Subdomain4.2 > Cyberattacks, weapon development or use, and mass harm; 7.2 > AI possessing dangerous capabilities
Entity2 - AI
Intent1 - Intentional
Timing3 - Other; 2 - Post-deployment
CategoryExtreme Risks; Model Capabilities
SubcategoryOffensive cyber capabilities

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-InfoComm2023-43.02.01 - Offensive cyber capabilities

"These evaluations focus on whether a LLM possesses certain capabilities in the cyber-domain. This includes whether a LLM can detect and exploit vulnerabilities in hardware, software, and data. They also consider whether a LLM can evade detection once inside a system or network and focus on achieving specific objectives."

Domain4. Malicious Actors & MisuseSubdomain4.2 > Cyberattacks, weapon development or use, and mass harmSourceCataloguing LLM EvaluationsYear2023

MITRISK-Tse2025-72.05.10 - Offensive cyber capability

"Ability to develop, deploy and operate advanced cyber weapons or other offensive cyber tools, including but not limited to vulnerability exploitation, network penetration, social engineering attacks and distributed attack systems, able to evade network defense mechanisms and establish persistent access channels."

Domain7. AI System Safety, Failures, & LimitationsSubdomain7.2 > AI possessing dangerous capabilitiesSourceFrontier AI Risk Management Framework (v1.0)Year2025

Mitigations

Defenses that may help with related attacks.

LifecycleData Preparation + 1 moreCategoryTechnical - ML
Data PreparationML Model Engineering
LifecycleBusiness and Data Understanding + 2 moreCategoryTechnical - Cyber
B&D UnderstandingData Preparation+1 more
LifecycleData Preparation + 3 moreCategoryTechnical - ML
Data PreparationML Model Evaluation+2 more

Showing 4 of 6

Source evidence

Research source for this risk, when available.