git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTION

Full Analysis

[COMMAND_EXECUTION]: The skill modifies configuration files (.claude/settings.json) to register a persistent PreToolUse hook that executes a script before the agent uses tools.
[COMMAND_EXECUTION]: Instructions include using chmod +x on the bundled scripts/block-dangerous-git.sh to enable execution within the agent environment.
[SAFE]: The skill is a defensive utility intended to limit the agent's authority and prevent destructive operations on the user's host system.

Audit Metadata

Risk Level

SAFE

Analyzed

Jun 15, 2026, 03:36 AM

Security Audit — agent-trust-hub — git-guardrails-claude-code