Notifications
Clear all
Topic starter
07/06/2026 8:52 pm
TL;DR: Most agentic security failures still begin with identity mistakes, not exotic model attacks: unauthorized access, excess permissions, and weak auditability are the issues that decide production risk, according to WorkOS. The practical lesson is that authentication, authorization, and lifecycle controls remain the baseline before specialised AI security tooling adds value.
NHIMG editorial — based on content published by WorkOS comparing HiddenLayer and WorkOS for agentic security
By the numbers:
- HiddenLayer has 25 granted patents covering their detection methodologies.
Questions worth separating out
Q: How should security teams govern access for production AI agents?
A: Security teams should govern AI agents as identities with explicit permissions, not as generic application features.
Q: Why do enterprise AI agents still depend on traditional IAM controls?
A: Enterprise AI agents still depend on traditional IAM controls because the main failure mode is usually unauthorized access or over-permission, not model reasoning alone.
Q: What do security teams get wrong about AI agent risk?
A: Security teams often over-focus on prompt injection and model extraction while underestimating access control failure.
Practitioner guidance
- Map agent access to explicit identities Assign every production agent, integration, and service path a named identity and enforce least privilege at the point of invocation.
- Tie authorization to runtime policy checks Validate each agent action against current user, resource, and data context instead of trusting session-level approval.
- Synchronize directory changes into agent entitlements Propagate joiner, mover, and leaver events into agent permissions so access changes follow the user lifecycle.
What's in the full article
WorkOS's full article covers the operational detail this post intentionally leaves for the source:
- Enterprise SSO integration specifics for common identity providers and protocol combinations
- Fine-grained authorization implementation detail for runtime agent permission checks
- Directory sync and provisioning behaviour for joiner, mover, and leaver events
- Audit logging and compliance-oriented controls that support enterprise sales and investigations
👉 Read WorkOS's comparison of HiddenLayer and WorkOS for agentic security →
Agentic security and IAM: what matters before specialised AI tooling?
Explore further
08/06/2026 8:35 am
Identity is the control plane for agentic security: Most production failures in agentic systems begin with who can access the agent and what that agent can do once invoked. AI-native detection may catch model misuse, but enterprise breach paths still run through authentication, authorization, and stale entitlement management. The field should stop treating agent security as a specialised overlay on top of IAM and recognise that IAM is the foundation the agent inherits.
A few things that frame the scale:
- Only 52% of companies can track and audit the data their AI agents access, leaving 48% with a complete blind spot for compliance and breach investigation, according to AI Agents: The New Attack Surface report.
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, inappropriately sharing sensitive data, and revealing access credentials.
A question worth separating out:
Q: How do you know if AI agent authorization is actually working?
A: Authorization is working when each agent action can be tied to a current identity, a current policy, and a specific data or resource scope. If access reviews cannot explain who approved the entitlement, or logs cannot reconstruct the decision, the control is not operationally effective.
👉 Read our full editorial: Agentic security starts with identity and authorization infrastructure
