Permitted vs observed: drift as a first-class finding
Drift between what an AI agent is permitted to do and what it is observed doing becomes a structured, classified finding with confidence levels.
Topic
least-privilege
Explore least-privilege articles from the Olivares AI blog on self-hosted governance, security and operations for enterprise AI agents.
What your AI agents can actually reach: mapping agent access on real infrastructure
An AI agent holds credentials, is permitted some actions, and is observed doing others. The access map shows the gap, and where least-privilege quietly broke.
Least-privilege drift: catching over-privileged AI agents before an incident
How to spot least-privilege drift in AI agents by comparing permitted access with observed behavior and enforcing policy at access time.
Passive discovery vs proxies: inventorying AI agents without sitting in the data path
Two ways to see your AI agents: an inline proxy with high blast radius, or passive discovery from logs, OpenTelemetry and an eBPF backstop. An honest tradeoff.