Agent Guard Secret Guardrails

Version updated for https://github.com/JeongJaeSoon/agent-guard to version v1.10.0.

  • This action is used across all versions by ? repositories.

Action Type

This is a Composite action.

Go to the GitHub Marketplace to find the latest changes.

Action Summary

Summary:

Agent Guard is a deterministic guardrail that blocks AI coding agents from accidentally exposing secrets during tool calls. It uses gitleaks for detection and plain shell scripts for integration. It runs at the agent’s tool boundary to block common secret exposure methods, such as reading .env files or writing sensitive values. Agent Guard pairs with commit/CI scanning for defense in depth. It is not a vault or credential rotator but provides real-time protection before secrets are exposed.

What’s Changed

What’s Changed

Full Changelog: https://github.com/JeongJaeSoon/agent-guard/compare/v1.9.0...v1.10.0