Topic starter
24/07/2026 4:09 pm
TL;DR: OpenAI AgentKit lowers the barrier to building AI agents inside a widely adopted platform, accelerating agent sprawl, expanding no-code workflow creation, and increasing the risk of unsanctioned data access and destructive actions, according to Noma Security. The governance problem is no longer agent capability alone, but visibility, approval gating, and policy control across workflows built outside AppSec review.
Editorial analysis by NHI Mgmt Group, based on content published by Noma Security: “OpenAI agentkit just democratized agent building, and multiplied your attack surface”.
Key questions
Q: What breaks when business users can build agents without security review?
A: The failure is not only unapproved automation.
Q: Why do flow agents create more risk than chat agents in enterprise apps?
A: Flow agents usually execute predefined business steps, but they often carry broader permissions and stronger operational authority than chat interfaces.
Q: What are the signs that an embedded agent workflow is misconfigured?
A: Look for untrusted input influencing variables, developer messages, approval logic, or file-search content.
Practitioner guidance
- Map every embedded agent to an owner and approval path Create a complete inventory of AgentKit workflows, the business owner behind each one, the systems it can touch, and the approval path required before any destructive action.
- Classify flow agents by blast radius, not interface type Separate chat agents from flow agents, then rank each workflow by its write access, external integrations, and ability to process payments, delete data, or change permissions.
- Block untrusted input from control fields Prevent user-supplied content from flowing into developer messages, variables, approval logic, or other fields that influence authorization, routing, or transaction handling.
Bottom line: OpenAI AgentKit changes the security problem by making agent creation widely accessible inside enterprise workflows, which expands the inventory and governance burden.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
24/07/2026 4:14 pm
Agent sprawl is now a governance problem, not a feature problem: When a platform makes agent building available to large numbers of business users, the control challenge shifts from design-time development to runtime governance. That change overwhelms review models built for a small number of centrally engineered automations. The practical conclusion is that discovery, ownership, and policy enforcement must scale with distribution, not with developer headcount.
A question worth separating out:
Q: How should security teams govern AI-enabled workflows that can act on their own?
A: Treat them as identity-governed execution paths, not just software features. Assign a named owner, define least-privilege access, log every tool call, and require revocation paths for credentials and tokens. If the workflow can touch production systems or sensitive data, its permissions must be reviewed with the same discipline used for privileged machine identities.
👉 Read our full editorial: OpenAI AgentKit expands AI agent sprawl across enterprise workflows