git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill installs a local bash script (
block-dangerous-git.sh) designed to intercept and validate Git commands before they are executed by the agent. - [PRIVILEGE_ESCALATION]: The setup process involves granting execution permissions (
chmod +x) to the provided guardrail script to enable its functionality. - [PERSISTENCE]: The skill modifies the agent's configuration files (
.claude/settings.jsonor~/.claude/settings.json) to permanently register the guardrail hook across future sessions.
Audit Metadata