git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill sets up a bash script (
block-dangerous-git.sh) that is executed by the agent's hook system to evaluate and potentially block incoming commands based on a predefined blacklist. - [SAFE]: The skill modifies agent configuration files (
.claude/settings.jsonor~/.claude/settings.json) to install persistent hooks. While this modifies the agent's long-term behavior, it is the primary stated purpose of the skill to provide continuous protection. - [SAFE]: The installation process includes using
chmod +xto grant execution permissions to the included guardrail script, which is a standard and necessary step for script-based hooks.
Audit Metadata