Topic starter
24/10/2026 9:48 pm
TL;DR: Trusted AI agents can expose credentials quickly because their behaviour can drift after deployment while access assumptions stay the same, as NetFoundry explains. Production agent governance depends on enforced access and network limits, not prompt-level hints.
Editorial analysis by NHI Mgmt Group, based on content published by NetFoundry: “Don’t Trust the Agent: Zero Trust for AI Agents”.
Key questions
Q: Why do model guardrails fail as a sole control for AI agents?
A: Guardrails influence the model's output, but they do not reliably stop an authorised runtime action once the agent can invoke tools.
Q: How do organisations know whether AI is truly under governance control?
A: They should be able to show where AI is recommend-only, where it can act, who owns each AI identity, what evidence is logged, and how access is revoked.
Q: What should teams do first when AI agents are already in production?
A: Teams should first inventory all agent identities, map the credentials they use, and verify that each one has a named sponsor and monitored workflow.
Practitioner guidance
- Define agent capability as code Describe each AI agent in declarative configuration so the approved tools, resources and actions are explicit and auditable.
- Start every agent at zero privilege Block ingress, egress, tools and file system access by default, then add only the minimum capabilities needed for the task.
- Move credentials behind mediated tools Keep API keys and other secrets behind the tools the agent calls, rather than exposing raw credentials directly to the runtime.
Bottom line: AI agents are operationally risky when their behaviour can change after deployment while access assumptions stay the same.
Glossary terms: Hard boundary, Soft boundary, Declarative Agent, Ephemeral trust debt
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
This topic was modified 6 days ago by NHI Mgmt Group
25/10/2026 11:12 am
Access review assumptions break down when the actor can change behaviour mid-session. The governance model behind access review assumes a relatively stable subject whose permissions can be observed, certified and revoked on a review cycle. That assumption fails when an AI agent can alter its behaviour overnight through model, alias or harness updates. The implication is not just more review cadence, but a recognition that the review window itself may be the wrong control boundary.
A few things that frame the scale:
- 19% of organisations give AI systems dramatically more access than human employees, nearly one in five granting unrestricted privilege, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: What is the difference between guardrails and hard boundaries for AI agents?
A: Guardrails are behavioural hints that shape output and reduce risk, while hard boundaries are enforced controls over access, tools and network paths. Guardrails can be bypassed by a capable runtime. Hard boundaries define what the agent is technically unable to do, which is why they belong at the centre of production design.
👉 Read our full editorial: Zero trust for AI agents needs hard boundaries, not guardrails
This post was modified 6 days ago by NHI Mgmt Group