Foundational LLMs

An existing foundation model is consumed for inference.

Classification definition is a project adaptation of the DASF deployment model descriptions. Source applicability is column L of AI Lifecycle Risks, snapshot 2026-10-22.

Combine patterns using union (OR). An agent that uses retrieval and a third-party model should include agentic-ai, rag and external-model; include foundation-llm if the model is a foundation model. Do not assume “pre-trained” means merely calling an already trained foundation model: this taxonomy distinguishes pretraining from consumption.

17 source-applicable risks:

• DASF-R-4.2 — Lack of end-to-end ML lifecycle
• DASF-R-6.3 — Lack of Interpretability and Explainability
• DASF-R-8.1 — Model attribution
• DASF-R-9.7 — Denial of Service (DoS)
• DASF-R-9.8 — LLM hallucinations
• DASF-R-9.11 — Model Inference API Access
• DASF-R-9.13 — Excessive agency
• DASF-R-10.1 — Lack of audit and monitoring inference quality
• DASF-R-10.2 — Output manipulation
• DASF-R-11.1 — Lack of MLOps — repeatable enforced standards
• DASF-R-12.1 — Lack of vulnerability management
• DASF-R-12.2 — Lack of penetration testing, red teaming and bug bounty
• DASF-R-12.3 — Lack of incident response
• DASF-R-12.4 — Unauthorized privileged access
• DASF-R-12.5 — Poor security in the software development lifecycle
• DASF-R-12.6 — Lack of compliance
• DASF-R-12.7 — Initial Access