Notifications
Clear all
Topic starter
10/06/2026 12:18 am
TL;DR: Agentic AI changes the threat model by adding memory poisoning, tool misuse, privilege compromise, untraceability, and identity spoofing to the risk stack, according to Lasso Security, while OWASP’s agentic AI guide is used to frame the control problem. The real shift is that governance now has to handle runtime behaviour, not just static permissions, because agent decisions can evolve after deployment.
NHIMG editorial — based on content published by Lasso Security: The Top Agentic AI Security Threats You Need to Know in 2026
By the numbers:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems (39%), inappropriately sharing sensitive data (31%), and revealing access credentials (23%).
Questions worth separating out
Q: How should security teams govern AI agents that can use tools and memory?
A: Security teams should treat AI agents as identities with runtime authority, not as ordinary applications.
Q: Why do AI agents create more identity risk than traditional LLM applications?
A: AI agents create more identity risk because they can persist state, choose tools, and carry out actions over time.
Q: What breaks when an AI agent inherits broad user privileges?
A: When an AI agent inherits broad user privileges, the boundary between intended assistance and unauthorised action collapses.
Practitioner guidance
- Map agent identity separately from application identity Document every agent, sub-agent, and delegated workflow as a distinct identity subject, then record which tools, datasets, and runtime actions each one can access.
- Scope credentials to a single agent purpose Issue session-scoped or task-scoped credentials that cannot be reused across unrelated workflows, and revoke access when the task is complete or the context changes.
- Treat memory as governed state Classify short-term and long-term memory stores by sensitivity, provenance, and retention rules, then add validation and rollback for poisoned or unexpected context.
What's in the full article
Lasso Security's full analysis covers the operational detail this post intentionally leaves for the source:
- Function-level policy examples for blocking unsafe tool invocation in agent workflows
- MCP Gateway guardrail behaviour for prompt monitoring, context boundaries, and session control
- Real-time logging patterns for model behaviour, prompt history, and decision points
- Identity-bound permission models for multi-agent deployments and delegated execution
👉 Read Lasso Security's analysis of the top agentic AI security threats for 2026 →
Agentic AI security threats in 2026: what IAM teams need to know?
Explore further
11/06/2026 2:01 am
Agentic AI is not just another NHI category. It collapses the boundary between identity, application, and decision-making, which means security teams can no longer assume that permission sets describe behaviour. The article’s threat list makes that clear by showing how memory, tools, and inherited privileges interact at runtime. That combination creates a control problem that sits across IAM, PAM, and application security, so practitioner programmes need a joined-up identity model rather than separate AI and NHI silos.
A few things that frame the scale:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems (39%), inappropriately sharing sensitive data (31%), and revealing access credentials (23%), according to AI Agents: The New Attack Surface report.
- 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.
A question worth separating out:
Q: How can organisations tell whether agentic AI controls are working?
A: Organisations can tell controls are working when each agent action is tied to a known identity, a narrow scope, and an auditable decision trail. If logs cannot show who or what acted, which tool was used, and why the action was allowed, governance is incomplete. Effective control reduces surprise behaviour, not just alert volume.
👉 Read our full editorial: Top agentic AI security threats in 2026 are shifting access risk
12/06/2026 3:36 am
Agentic AI is not just another NHI category. It collapses the boundary between identity, application, and decision-making, which means security teams can no longer assume that permission sets describe behaviour. The article’s threat list makes that clear by showing how memory, tools, and inherited privileges interact at runtime. That combination creates a control problem that sits across IAM, PAM, and application security, so practitioner programmes need a joined-up identity model rather than separate AI and NHI silos.
A few things that frame the scale:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems (39%), inappropriately sharing sensitive data (31%), and revealing access credentials (23%), according to AI Agents: The New Attack Surface report.
- 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.
A question worth separating out:
Q: How can organisations tell whether agentic AI controls are working?
A: Organisations can tell controls are working when each agent action is tied to a known identity, a narrow scope, and an auditable decision trail. If logs cannot show who or what acted, which tool was used, and why the action was allowed, governance is incomplete. Effective control reduces surprise behaviour, not just alert volume.
👉 Read our full editorial: Top agentic AI security threats in 2026 are shifting access risk
