[AdvaitVarhade]

Fixes #110

Adds a security rule for AI Agent Skill definitions to ensure that autonomous agents are operating with appropriate tool constrainment, filesystem/network boundaries, and auditing. Also registers the agents tag to categorize these rules.

[CLAassistant]

All committers have signed the CLA.

[AdvaitVarhade]

I have read the CLA Document and I hereby sign the CLA

[github-actions]

This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[AdvaitVarhade]

Hello. I am checking in on this pull request to keep it active and prevent automatic stale closure. The Contributor License Agreement is signed and the security rule is ready for evaluation. Please check and tell if any changes are required.

[thomas-bartlett]

Thanks for following up, @AdvaitVarhade, and apologies for the delay. We’re focusing on testing to validate the direction for CodeGuard 2.0 before asking you to revise this contribution.

We want to preserve your work and avoid repeated rework as the direction settles. We’ll follow up with a clearer next step; no changes are needed from you right now.