AI Risk Frameworks: NIST AI RMF and OWASP LLM Top 10

Intermediate

You don't have to invent your own checklist

01 The Concept

You don't need to build an AI risk taxonomy from scratch — two frameworks, both first published in 2023, cover most of the ground. The NIST AI Risk Management Framework gives a governance-level structure (govern, map, measure, manage) for organizations deploying AI broadly, useful for policy and audit conversations. The OWASP Top 10 for LLM Applications is far more hands-on: a ranked, community-maintained list of concrete vulnerability classes (prompt injection, insecure output handling, training data poisoning, supply chain, excessive agency, and more) written for engineers actually building the thing, and updated as new attack classes emerge.

Using both together works well in practice: OWASP's list gives you a technical checklist to design and review against; NIST's framework gives you the organizational process (who owns AI risk, how it's measured, how it's reported) that makes the technical checklist stick instead of being a one-time exercise.

02 Case Study

CASEOWASP Top 10 for LLM Applications — community working group process (2023, updated as new attack classes emerge)

Unlike a single-vendor security bulletin, OWASP's list is written and revised by a working group of practitioners — people actually building and defending LLM applications at different companies — pooling documented incidents and disclosed research into a single ranked, engineer-facing list: prompt injection, insecure output handling, training data poisoning, supply chain risk, excessive agency, and more. Because it's community-maintained rather than a one-time report, categories have been added and reordered as new attack classes (like many-shot jailbreaking) were disclosed and understood well enough to name precisely.

→ Why it matters

The practical value isn't that OWASP invented anything new — it's that a team building an LLM feature can review it against a checklist reflecting the pooled experience of the wider field, instead of only the vulnerability classes any one team happened to already think of.

03 Key Points

01NIST AI RMF = organizational governance structure (govern, map, measure, manage), published 2023

02OWASP LLM Top 10 = concrete, engineer-facing, community-maintained vulnerability checklist, also from 2023

03Use OWASP for technical design/review, NIST for ownership and process

04Neither framework replaces threat modeling your specific application — both are starting points

Next: Least-Privilege Tool Use for AI Agents →