Topic starter
02/08/2026 12:28 pm
TL;DR: Agentic AI raises security risk because memory, tool use, and recursive execution let software behave like a persistent actor rather than a bounded interface, according to Promptfoo. Identity and access controls now need to move closer to agent actions if organisations want to limit misuse and drift.
Editorial analysis by NHI Mgmt Group, based on content published by Promptfoo: “Autonomy and agency in AI: We should secure LLMs with the same fervor spent realizing AGI”.
By the numbers:
- Gartner predicts over 40% of agentic AI projects will be canceled by the end of 2027.
- AI spending is to hit USD 375 billion this year alone.
- AI spending is to hit USD 500 billion next year.
Key questions
Q: Why do AI coding agents create access and governance risk even when they are not autonomous?
A: Because they already operate with tool access, repository access, and execution permissions inside a live workflow.
Q: What are the signs that an AI agent is failing or drifting outside its intended mission?
A: Common warning signs include goal drift, repeated no-progress calls, unusual tool use, privilege escalation attempts, credential misuse, and unexpected agent-to-agent communication.
Q: What breaks when memory isolation is weak in agentic AI systems?
A: Weak memory isolation lets context leak across sessions, which can expose sensitive data, preserve attacker-influenced state, or distort later decisions.
Practitioner guidance
- Define explicit agent boundaries Specify which goals, tools, data sources, and downstream actions each agent is allowed to use, then block everything else by default.
- Constrain memory and execution time Limit long-term memory, session persistence, and recursive task chaining so agents cannot continue acting after the original business purpose ends.
- Require approval for sensitive actions Insert human confirmation before an agent can access privileged systems, exfiltrate data, or trigger external side effects.
Bottom line: Agentic AI raises security risk because memory, tool use, and recursive execution let software behave like a persistent actor rather than a bounded interface.
Glossary terms: Autonomy, Agentic AI, Agency, Answer Drift
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
This topic was modified 2 days ago by NHI Mgmt Group
02/08/2026 1:27 pm
Agentic AI creates an NHI governance problem before it creates an AI safety problem. Once a model can hold memory, call tools, and continue execution, it behaves like a non-human actor whose access needs lifecycle controls, not just prompt discipline. That means inventory, authorization, revocation, and logging matter as much here as they do for other non-human identities. Practitioners should govern these systems as dynamic machine actors, not as chat interfaces with extra features.
A few things that frame the scale:
- Gartner predicts that more than 40% of agentic AI projects will be cancelled by the end of 2027, citing rising costs, unclear value and insufficient risk controls.
A question worth separating out:
Q: Should organisations treat AI as an application or as an identity?
A: Treat it as an identity when the AI can access data, invoke tools, or participate in workflows that affect business systems. That framing makes least privilege, just-in-time access, and lifecycle governance relevant. If you keep treating it only as an application, you will miss the access and delegation behaviours that actually create risk.
👉 Read our full editorial: AI agent autonomy and agency are widening security risk faster than controls