Analysis · curated 25 Sep 2026
How AI Agents Get Too Much Access to Company Systems
First reported aisty.ai
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
Excessive agency turns an AI agent's misstep, hallucination, or a hidden prompt injection into a real incident, so defenders need to scope agent access and enforce human checkpoints on high-impact actions.
Aisty's guide explains how AI agents accumulate excessive access to company systems through borrowed human credentials, broad default OAuth scopes, shared service accounts, scope creep, tool/MCP sprawl, and unattended autonomy — what OWASP terms 'excessive agency'. It notes dangerous combinations such as an agent that reads untrusted email plus one that sends email creating an exfiltration path, and recommends per-agent credentials, task-scoped permissions, separating read from act, human approval on high-impact actions, logging, and periodic access review.