Notifications
Clear all
Topic starter
07/06/2026 8:26 pm
TL;DR: AI agent security expands the attack surface because agents can act across tools, APIs, and workflows, with risks including prompt injection, excessive permissions, supply chain compromise, and weak runtime monitoring, according to WitnessAI. Traditional IAM controls still matter, but autonomous execution makes policy, observability, and accountability the decisive control plane.
NHIMG editorial — based on content published by WitnessAI: AI Agent Security and the controls needed to protect agentic systems
By the numbers:
- 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.
- When AWS credentials are exposed publicly, attackers attempt access within an average of 17 minutes, and as quickly as 9 minutes in some cases.
Questions worth separating out
Q: How should security teams govern AI agents that can use enterprise tools?
A: Security teams should govern AI agents as active identities with named ownership, task-scoped permissions, runtime monitoring, and explicit revocation paths.
Q: Why do AI agents create more identity risk than chatbots?
A: AI agents create more identity risk because they can do more than produce text.
Q: What do organisations get wrong about least privilege for AI agents?
A: They often apply least privilege to the initial login while ignoring the tools and data the agent can reach during execution.
Practitioner guidance
- Classify agents as governed identities Place every production agent into the identity inventory with a named owner, declared purpose, and explicit access boundary.
- Scope tool access to task boundaries Remove broad, reusable permissions from agent-linked credentials and replace them with task-scoped access to specific APIs, datasets, and endpoints.
- Monitor runtime actions, not only sign-ins Log agent tool calls, data reads, writes, and repeated automation loops, then alert on behaviour that deviates from the declared task.
What's in the full article
WitnessAI's full article covers the operational detail this post intentionally leaves for the source:
- Specific control patterns for runtime observation of agent actions, API calls, and outputs
- The article's breakdown of guardrails for prompt injection, excessive permissions, and workflow abuse
- Practical guidance on combining zero trust principles with incident response for compromised agents
- The vendor's framing of how to protect models, applications, and agents within one platform context
👉 Read WitnessAI's analysis of AI agent security and runtime control →
AI agent security and IAM controls: are your guardrails enough?
Explore further
07/06/2026 10:19 pm
AI agent security is now an identity governance problem, not just an application security problem. Once an agent can select tools, move through workflows, and touch enterprise systems, the relevant question becomes who or what is allowed to act, under what scope, and with what revocation logic. Traditional app security focuses on code and requests; agent security must govern behaviour and delegated authority. The practitioner conclusion is that agents should be treated as active identities, not passive software features.
A few things that frame the scale:
- 98% of companies plan to deploy even more AI agents within the next 12 months, despite documented rogue behaviour in 80% of current deployments, according to AI Agents: The New Attack Surface report.
- Only 44% have implemented policies to govern AI agents, even though 92% say that governing them is critical to enterprise security.
A question worth separating out:
Q: Should organisations use different controls for AI agents and human users?
A: Yes. Human IAM can rely heavily on authentication events and periodic access reviews, but AI agents require continuous behavioural controls because they can act without direct human timing. The right model combines identity governance, PAM-style scoping, runtime monitoring, and incident containment for machine actions, not just user sessions.
👉 Read our full editorial: AI agent security exposes the limits of traditional IAM controls
