# New framework guardscope checks LLM agent control coverage

> guardscope lets developers verify which action paths runtime controls actually inspect in LLM agents.

Oossa · 2026-11-13 · https://oossa.com/en/new-framework-guardscope-checks-llm-agent-control-coverage

Researchers released guardscope, a tool that measures how well runtime controls watch LLM agents’ actions. The framework first predicts which of an agent’s 15 possible action paths a control can see, then runs a workload on one of eight deployment topologies to label each action as checked, bypassed or prevented. Experiments used two agent harnesses and Microsoft’s governance toolkit and agentgateway. The code and framework are publicly available.

## The facts

- guardscope predicts coverage for 15 action paths and tests on eight topology designs.
- The paper evaluated Microsoft’s agent governance toolkit and agentgateway.

## Why it matters

Enterprises can now confirm that their safety controls actually see the actions they intend to monitor.

## Sources & references

1. [guardscope: Measuring Which Actions Runtime Controls Check in LLM Agent Systems](https://arxiv.org/abs/2611.15223) – arXiv, 2026-11-13

Last updated: 2026-11-13