# guardscope checks which AI agent actions security controls inspect

_Published Saturday, November 14, 2026 at 5:05 AM EST · Science, Security · Latest · Tier 2 — Notable_

Researchers released guardscope, a framework for measuring which AI agent actions security controls actually inspect, according to an arXiv preprint. It compares control decision records with operating-system kernel records to classify executed actions as checked, bypassed, or prevented.

The framework first examines control source code to predict coverage across 15 action paths, then tests a fixed workload in one of eight deployment designs. Researchers report experiments with two agent harnesses and controls including Microsoft's agent governance toolkit and agentgateway. The framework measures inspection coverage; an agent can take actions through paths beyond the tool calls a gateway checks.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2611.15223)

---
Canonical: https://techandbusiness.org/newswire/qwqwHJ4i6h6rg1mnf3reO4
Published: 2026-11-14T10:05:58.217Z
Story chronology: 2026-11-14T05:00:00.000Z
Retrieved: 2026-11-15T00:01:50.152Z
Publisher: Tech & Business (techandbusiness.org)