git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to create a local bash script (
scripts/block-dangerous-git.sh) and grant it execution permissions usingchmod +x. This script serves as a local safety hook.\n- [SAFE]: The skill modifies the Claude Code configuration files (.claude/settings.json) to register the hook script. This is the platform-native method for implementing guardrails and does not involve malicious persistence or privilege escalation.\n- [SAFE]: The logic in the hook script is defensive and transparent, using standard tools likejqandgrepto parse inputs and block a predefined list of dangerous git patterns.
Audit Metadata