The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a local shell script (block-dangerous-git.sh) and the jq utility to intercept and inspect commands requested by the AI agent. This is a defensive implementation designed to increase user control over destructive operations.
[EXTERNAL_DOWNLOADS]: References official documentation from Google's GitHub repository and Google Codelabs for configuration guidance. These references are to well-known, trusted sources and are used for instructional purposes.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution was found. The skill operates locally and follows the standard configuration patterns for the tools it supports (Claude Code, Cursor, and Gemini CLI).

git-guardrails