Notifications
Clear all
Topic starter
02/08/2026 9:45 am
TL;DR: The NIST AI Risk Management Framework gives organisations a governance structure for trustworthy AI, but for agentic and LLM applications it still leaves key technical gaps around tool permissions, prompt injection, and runtime control, according to Akto’s guide. The practical issue is that AI security now depends on continuous discovery, measurement, and enforcement, not policy alone.
NHIMG editorial — based on content published by Akto: NIST AI Security Framework practical guide for LLM apps
By the numbers:
- NIST published AI RMF 1.0 on January 26, 2023, following input from more than 240 contributing organizations across industry, academia, civil society, and government.
- NIST's Generative AI Profile, published as NIST AI 600-1 on July 26, 2024, identifies 12 risk categories unique to or amplified by generative AI.
- The OWASP Top 10 for LLM Applications 2025 ranks prompt injection as the top risk for the second consecutive edition.
Questions worth separating out
Q: How should security teams implement the NIST AI RMF for agentic AI systems?
A: Start with Govern and Map, but do not stop at policy and inventory.
Q: Why do agentic AI systems complicate identity governance more than traditional service accounts?
A: Traditional service accounts usually follow fixed workflows, while agentic systems can choose actions and sequence them at runtime.
Q: What breaks when organisations treat NIST AI RMF as a policy document only?
A: Measure becomes weak or absent, Manage becomes reactive, and the organisation loses visibility into how the live system behaves.
Practitioner guidance
- Map every AI tool connection as a privilege decision Treat each database, email, ticketing, or payment connector as a distinct access path with an owner, scope, and expiry model.
- Add continuous red teaming to Measure and Manage Run recurring tests for prompt injection, tool misuse, memory poisoning, and output leakage, then route the findings into remediation workflows with clear ownership.
- Build runtime guardrails around agent actions Enforce policy at execution time so risky tool calls are blocked or flagged before the agent completes the task.
What's in the full article
Akto's full guide covers the operational detail this post intentionally leaves for the source:
- A practical walkthrough of how the vendor maps Govern, Map, Measure, and Manage to AI security workflows.
- Continuous discovery and red teaming examples for LLMs, agents, and MCP server connections.
- Runtime guardrail examples for tool misuse, memory poisoning, and prompt injection.
- Implementation lessons from applying the framework in live AI environments.
👉 Read Akto's practical guide to the NIST AI security framework for LLM and agentic systems →
NIST AI RMF and agentic AI security: are your controls keeping up?
Explore further
02/08/2026 12:38 pm
NIST AI RMF is necessary governance scaffolding, not a complete security control set. The framework gives organisations a shared language for AI risk, but it stops short of telling security teams how to secure tool calls, limit memory abuse, or govern model-linked credentials. That is why AI governance programs must pair NIST AI RMF with prescriptive controls from agentic AI and NHI security practice. The practical conclusion is simple: the framework defines responsibility, not enforcement.
A question worth separating out:
Q: Which controls matter most when AI agents can use external tools?
A: Focus on tool authorisation, runtime policy enforcement, continuous discovery, and evidence-based monitoring. If an agent can reach databases, email, or payment workflows, the controls should limit scope, record actions, and prevent high-risk operations unless they are explicitly approved and auditable.
👉 Read our full editorial: NIST AI RMF for agentic systems: what practitioners need to operationalize
