TL;DR: AI agents are being used as active operators in intrusion chains, with Starseer reporting that identity, authorization, and session governance now sit inside the attack surface. Runtime controls have to follow the sequence of tool calls, or output review will miss a malicious chain that unfolds through legitimate actions.
Editorial analysis by NHI Mgmt Group, based on content published by Starseer: “AI Agents Are Now Running Full Cyberattacks, Unsupervised”.
By the numbers:
- A separate campaign compromised at least 440 servers across 395 organizations in 48 countries.
Key questions
Q: Why do AI agent attacks require runtime monitoring instead of output review?
A: Because the harmful behaviour often lives in the sequence of tool calls, not in the final answer.
A: Security teams should assume an agent can move from benign assistance to harmful action if a target system has weak authorization controls.
Q: What breaks when AI agents are given broad standing access?
A: Broad standing access breaks governance because the agent can move from one task to another without a fresh authorization check.
Practitioner guidance
- Map every AI agent to a distinct identity record Record which agent, service account, or delegated token is allowed to act, which tools it can reach, and when that authority expires.
- Log tool calls as security events Capture each request, response, and action outcome so analysts can reconstruct the full session sequence instead of only the final model output.
- Split read, write, and export privileges Prevent an agent from using one broad integration token to discover data, modify state, and exfiltrate content in the same session.
Bottom line: AI agents are being used as active operators in intrusion chains, which makes identity, authorization, and session governance part of the attack surface.
Glossary terms: Agentic AI, Runtime Governance, Agent Identity, Tool Misuse
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Agentic abuse is now a runtime governance problem, not a content-safety problem. The article shows that the dangerous behaviour emerges in the sequence of tool calls, not in any single model response. That means organisations that only review prompts or outputs will miss the real control failure. The practitioner implication is to govern action order, authority, and state transitions as first-class security objects.
A few things that frame the scale:
- 53% of security leaders expect AI to run major portions of their infrastructure autonomously within the next three years, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
A: A scripted automation process follows predetermined steps and fails in predictable ways. An autonomous AI agent can interpret context, choose actions, and adapt its approach while running, which creates a much larger control problem. That difference matters because containment, approval, monitoring, and incident response must assume the system may improvise, not simply execute a fixed workflow.
👉 Read our full editorial: AI agents are turning cyberattacks into runtime loops