git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill installs and configures a local shell script (
block-dangerous-git.sh) intended to intercept and validate Git commands before execution. - [COMMAND_EXECUTION]: During the setup process, the skill instructs the agent to grant execution permissions to the script using the
chmod +xcommand. - [SAFE]: The skill modifies the agent's configuration files (specifically
.claude/settings.jsonand~/.claude/settings.json) to implement the PreToolUse hook. This behavior is necessary for the skill's stated purpose of providing safety guardrails and does not represent an unauthorized persistence mechanism.
Audit Metadata