Version updated for https://github.com/JeongJaeSoon/agent-guard to version v3.0.0. 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 Agent Guard is an AI coding agent guardrail that blocks common secret leaks before they happen, protecting sensitive information like .env files and credentials from accidental exposure. It uses gitleaks for detection and shell scripts for integration, with support for Claude Code, Codex, Git hooks, CLI usage, and more.

Version updated for https://github.com/JeongJaeSoon/agent-guard to version v2.2.0. 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 Agent Guard is a guardrail for AI coding agents (Claude Code, Codex) to prevent accidental exposure of secrets before they are read or written. It uses gitleaks for detection and plain shell scripts for integration. By running at the agent’s tool boundary, it blocks common ways an agent can accidentally expose secrets and provides defense in depth by also performing commit- or CI-time scanning.

Version updated for https://github.com/JeongJaeSoon/agent-guard to version v2.1.0. 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 Agent Guard is a real-time guardrail that blocks AI coding agents from accidentally exposing secrets, such as reading .env files or writing secret-like values. It uses gitleaks for detection and provides shell scripts for integration into the agent’s tool boundary. The action helps prevent leaks before they occur by blocking sensitive file access and providing defense in depth with commit/CI scanning.

Version updated for https://github.com/JeongJaeSoon/agent-guard to version v2.0.1. 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 Agent Guard is a deterministic guardrail designed to prevent AI coding agents from accidentally exposing sensitive information, such as .env files containing private keys or credentials. It monitors the agent’s interactions with these files at runtime and blocks them if they attempt to read or write sensitive data before it can be used. This tool helps in real-time detection of potential leaks by using gitleaks for scanning and plain shell scripts for integration, ensuring defense-in-depth security measures are implemented.

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.

Version updated for https://github.com/JeongJaeSoon/agent-guard to version v1.7.1. 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. What’s Changed What’s Changed fix(shell): make setup-shell rc line self-healing when the CLI leaves $PATH by @JeongJaeSoon in https://github.com/JeongJaeSoon/agent-guard/pull/96 release: v1.7.1 by @github-actions[bot] in https://github.com/JeongJaeSoon/agent-guard/pull/97 Full Changelog: https://github.com/JeongJaeSoon/agent-guard/compare/v1.7.0...v1.7.1

Version updated for https://github.com/JeongJaeSoon/agent-guard to version v1.7.0. 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. What’s Changed What’s Changed feat(shell): resolve agent-guard without a PATH install for the bang guard by @JeongJaeSoon in https://github.com/JeongJaeSoon/agent-guard/pull/94 release: v1.7.0 by @github-actions[bot] in https://github.com/JeongJaeSoon/agent-guard/pull/95 Full Changelog: https://github.com/JeongJaeSoon/agent-guard/compare/v1.6.0...v1.7.0

Version updated for https://github.com/JeongJaeSoon/agent-guard to version v1.5.0. 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. What’s Changed What’s Changed feat(detection): broaden output secret recall (JWT, bearer, more env keys) by @JeongJaeSoon in https://github.com/JeongJaeSoon/agent-guard/pull/85 feat(shell): mask ! shell-escape output via agent-guard exec + shell-init by @JeongJaeSoon in https://github.com/JeongJaeSoon/agent-guard/pull/86 release: v1.5.0 by @github-actions[bot] in https://github.com/JeongJaeSoon/agent-guard/pull/88 Full Changelog: https://github.com/JeongJaeSoon/agent-guard/compare/v1.4.0...v1.5.0