Threat Taxonomy

A threat taxonomy is a structured classification of the ways AI systems can cause harm or be attacked, grouping risks into categories such as misuse, data leakage, manipulation of model behavior, and failures of reliability or safety. For compliance and risk teams, it provides a common vocabulary for cataloguing AI risks, mapping them to controls, and showing regulators or boards that known failure modes have been systematically considered. Frameworks such as the MITRE ATLAS knowledge base and the OWASP Top 10 for large language model applications are widely used examples that organizations reference when building their AI risk registers.

1 item

StandardsGlobal2026-10-19

MITRE ATT&CK v20 Names Prompt Injection and AI Agent Abuse as Formal Threat Categories

MITRE has released version 20 of its ATT&CK framework, adding formal entries for AI-specific attack techniques. New entries cover prompt injection against AI models, abuse of AI agents to steal data, and poisoning of web content to skew AI search results. Compliance and risk teams at organizations using AI agents or AI-assisted security tools now have a recognized threat taxonomy to map against their controls.

MITRE ATT&CK prompt injection AI agent abuse critical infrastructure threat taxonomy agentic AI red teaming