Topic starter
25/06/2026 12:48 am
TL;DR: AI agents are beginning to access secrets, APIs, and infrastructure directly, which expands the identity attack surface and exposes audit gaps when traditional PAM is built for human users, according to Delinea. The governance problem is not AI capability itself but the assumption that access can still be handed out, logged, and reviewed like a normal human workflow.
Editorial analysis by NHI Mgmt Group, based on content published by Delinea: “Unlocking AI Agents with Delinea MCP Server”.
Key questions
Q: What fails when AI agents are given raw secrets instead of mediated access?
A: Raw secrets turn an AI agent into a bearer of privileges rather than a governed requester.
Q: Why do multi-agent systems create audit and accountability gaps in enterprise AI workflows?
A: They distribute work across multiple agents, tools, and model calls, which makes execution easy to trace but harder to govern.
Q: How should teams govern AI agents that use MCP?
A: Treat each connected agent as a non-human identity with an owner, a scope, and a review cycle.
Practitioner guidance
- Map every AI workflow to an identity subject Inventory which copilots, agents, scripts, and assistants can reach secrets, APIs, or infrastructure, and record whether each is human-triggered, agent-triggered, or fully automated.
- Replace raw secret delivery with mediated access Use short-lived tokens or policy-checked access responses instead of exposing reusable secrets directly to the agent or model context.
- Bind logging to the full identity decision chain Capture the initiating actor, policy decision, requested resource, and credential form in the same audit record so investigations can reconstruct the access path.
Bottom line: AI agents accessing secrets and APIs create an identity governance problem that human-era PAM does not describe well.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
25/06/2026 9:48 am
AI agent identity is now a policy problem, not just an access problem: once an agent can request secrets, call APIs, and trigger workflows, the control question becomes what policy decides the action, not whether the model can perform it. Human-era PAM assumes a person can be placed inside a reviewable access path. AI agents break that assumption because the requester and executor may be the same runtime object, and the path from request to action can be machine-paced. Practitioners need to treat the agent as an identity subject with enforceable boundaries, not a convenience layer over existing credentials.
A few things that frame the scale:
- 88% of organisations have embedded AI agents in their workflows, according to KPMG's 2026 report.
A question worth separating out:
Q: When does an AI agent become an autonomous identity risk?
A: An AI agent becomes an autonomous identity risk when it can independently choose actions, select tools, and execute timing without human approval. At that point, fixed NHI controls are no longer enough because the actor can change scope mid-session. Until then, most agent workflows should be governed as non-autonomous machine identities.
👉 Read our full editorial: AI agent identity needs policy and audit controls, not raw secrets