git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to improve security by preventing an AI agent from accidentally running destructive Git operations. It provides a simple Bash script that checks command strings against a blocklist.
- [COMMAND_EXECUTION]: The skill involves creating and executing a local shell script (
git-guardrails.sh) and setting permissions withchmod +x. These are standard administrative actions required to install the hook system it describes. - [PERSISTENCE]: The instructions involve modifying
.claude/settings.jsonto register aPreToolUsehook. While this persists across agent sessions, it is the primary and intended function of the skill to maintain a consistent safety guardrail. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill only interacts with local configuration files for Claude Code and does not perform any network operations or access sensitive system credentials.
Audit Metadata