Topic starter
15/08/2026 6:12 pm
TL;DR: AI agents are creating new security vulnerabilities through prompt injection, token compromise, excessive privilege, and data exfiltration, while traditional controls struggle to govern systems that learn, adapt, and act independently, according to Obsidian Security. The governance gap is structural: existing IAM assumes stable, reviewable access, but agent behaviour changes at runtime.
Editorial analysis by NHI Mgmt Group, based on content published by Obsidian Security: “Top AI Agent Security Risks and How to Mitigate Them”.
By the numbers:
- 90% of agents hold excessive privileges, creating a gap between claimed configuration and effective authority.
- AI agents move 16x more data than human users performing equivalent tasks, which dramatically expands the blast radius of any single compromised agent.
Key questions
Q: What breaks when AI agents have broader access than their tasks require?
A: Over-privileged agents break segregation of duties, weaken auditability, and expand blast radius across transactions, data lookups, and workflow triggers.
Q: Why do stolen tokens and API keys make ransomware harder to contain?
A: Tokens and API keys often authenticate as legitimate machine or service identities, which means they can bypass the suspicion attached to obvious malware.
Q: How can security teams tell whether AI agent approval controls are actually working?
A: Look for evidence that sensitive actions trigger a fresh approval event, that approvals are tied to a specific human principal, and that the agent cannot proceed when the checkpoint fails.
Practitioner guidance
- Constrain agent scopes to task-level reachability Define each agent's allowed data sources, write paths, and external destinations as narrowly as the workflow allows.
- Replace static keys with short-lived credentials Use certificates or short-lived tokens where possible, and make rotation automatic for every credential tied to an agent.
- Instrument runtime behavioural baselines Track normal query volume, call sequences, response patterns, and sensitive data access so deviations are visible before exfiltration.
Bottom line: AI agents create identity risk because their access, tool use, and data reach can change at runtime in ways static IAM was not built to govern.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
15/08/2026 6:19 pm
AI agent security is an identity governance problem before it is an application security problem. The article shows that the main risk comes from how agents authenticate, accumulate privilege, and act across systems, not from model behaviour alone. That shifts the centre of gravity from static application review to runtime identity control. Practitioners should treat agent identity as a governed execution subject, not a software feature.
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.
- Systems with least-privileged AI access had a 17% incident rate vs 76% for over-privileged systems. Organisations failing to scope AI access properly are 4.5x more likely to experience a security incident, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
A: Organisations should treat SaaS agents as shared-control systems and insist on runtime policy that covers data access, tool use, downstream actions, tenant isolation, and auditability. The practical test is whether the enterprise can enforce its own rules even when the vendor owns the execution environment. If it cannot, the agent is configurable, but not truly governed.
👉 Read our full editorial: AI agent security risks expose gaps in traditional IAM controls