git-guardrails-claude-code
Warn
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill establishes persistence by modifying the agent's configuration files (
~/.claude/settings.jsonor.claude/settings.json) to install aPreToolUsehook. This hook ensures the blocking script is executed automatically before every Bash tool invocation. - [COMMAND_EXECUTION]: The skill requires the user to grant execution permissions to a local script using
chmod +x. This script then runs with the agent's privileges during tool use. - [COMMAND_EXECUTION]: The provided bash script (
scripts/block-dangerous-git.sh) relies on the external system dependencyjqto parse tool input, which must be pre-installed on the host system.
Audit Metadata