Topic starter
06/07/2026 9:38 am
TL;DR: Agentic failures emerge across prompts, tool calls, memory, and multi-step execution in NVIDIA NeMo Agent Toolkit, with structured scoring and risk propagation revealing where attacks succeed or spread, according to Lakera. The real lesson is that model checks alone cannot govern workflow-level behaviour when the execution layer is where risk compounds.
Editorial analysis by NHI Mgmt Group, based on content published by Lakera: “Red Teaming Agentic Capabilities in NVIDIA NeMo Agent Toolkit”.
Key questions
Q: What breaks when agentic AI red teaming stays at single prompts?
A: Single-prompt testing misses stateful failures that emerge only after tool calls, memory updates, and follow-on decisions interact.
Q: Why do agent workflows create more governance risk than standalone models?
A: Agent workflows create more governance risk because they combine reasoning with action.
Q: How do security teams know if AI red teaming is working?
A: AI red teaming is working when testing finds real prompt injection paths, over-scoped integrations, and policy gaps before attackers do, and when fixes are re-tested successfully after model or workflow changes.
Practitioner guidance
- Map the full agent workflow Document user inputs, tool boundaries, intermediate state, memory, and handoff points before you treat the system as testable or governable.
- Run end-to-end red team scenarios Exercise the agent across complete execution paths, including indirect inputs and tool responses, so you can observe how failures emerge downstream.
- Track risk propagation, not just attack success Compare where a failure starts, where it spreads, and where it is filtered so you can distinguish local weakness from workflow-wide brittleness.
Bottom line: Agentic AI red teaming has to evaluate the full execution layer because workflow behaviour can create risk that prompt-only checks never see.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
06/07/2026 9:53 am
Execution-layer governance is now the right unit of control for agentic AI. The article’s central point is that prompt checks do not describe the real security boundary once an agent can call tools, retain state, and hand work across steps. That moves the governance question from what the model said to what the workflow did. Practitioners should treat the execution path as the unit of risk.
A question worth separating out:
Q: What should teams do after an agent red team run finds workflow weaknesses?
A: They should fix the weak execution points, then rerun the same scenarios against the updated system. The goal is to prove that guardrails, output validation, or prompt changes altered behaviour across the full workflow, not only at the model boundary.
👉 Read our full editorial: Red teaming agentic AI workflows is now an execution-layer problem