Agentic AI

https://taxonomy.eticas.ai/risk/agentic-ai

Maturity: established

Risks arising from AI systems that autonomously plan, reason, and act across multiple steps using tools, memory, and external services, beyond single-inference interactions. These risks are distinct from standard LLM risks because the agent takes real-world actions, operates across time, and interacts with external systems and other agents.

Also known as: AI Agents · Agentic risks

System type: Large language models (LLM)
Lifecycle stages: Post Processing

Risk groups

• Autonomous Actions and Tool Use — Risks from the agent taking real-world actions through external tools, APIs, and services, including being granted excessive permissions, executing unnecessary or out-of-scope actions, bypassing human oversight, or consuming disproportionate resources.
• Multi-agent Integrity — Risks from systems composed of multiple agents — including trust exploitation, cascading failures, goal misalignment between agents, and insufficient traceability across the pipeline.

Mappings to external frameworks

Status. Each mapping shows what it rests on. Reviewed means a reviewer has confirmed the mapping against the concept’s current definition and the framework edition the taxonomy currently references; when the only confirmation is that of the person who wrote the mapping, it reads Reviewed (author’s confirmation). Outdated means it was reviewed, but the concept’s definition has changed since, so the review has to be repeated. The other statuses mean that no review has been recorded yet. Inherited mappings have been in the taxonomy since before v5.7.0 and are unchanged. They carry no record of who made them or how, and some were checked by hand when the taxonomy first published its mappings. Agent-proposed mappings come from a review carried out by AI agents, which read the framework’s text and the concept’s definition and agreed on the relation; no person has confirmed them yet. Provisional mappings were made without access to the framework’s text. Unreviewed mappings are older mappings whose target or relation was revised in v5.7.0, and any other mapping without a review. Mappings to a superseded edition of a framework are not shown: where the provision continues, they are carried to the current edition. Mappings a review has changed or rejected are not shown.

Standards & frameworks

Taxonomies & vocabularies